The project automatically fetches the latest papers from arXiv based on keywords.
The subheadings in the README file represent the search keywords.
Only the most recent articles for each keyword are retained, up to a maximum of 100 papers.
You can click the 'Watch' button to receive daily email notifications.
Last update: 2024-09-12
- Time Series
- LLM
- Image Restoration
- Diffusion Model
- Vision Language Model
- Photoacoustic Image
- Prompt Optimization
| Title | Date | Abstract | Comment |
|---|---|---|---|
| Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust | 2024-09-10 | ShowMachine learning models play a vital role in time series forecasting. These models, however, often overlook an important element: point uncertainty estimates. Incorporating these estimates is crucial for effective risk management, informed model selection, and decision-making.To address this issue, our research introduces a method for uncertainty estimation. We employ a surrogate Gaussian process regression model. It enhances any base regression model with reasonable uncertainty estimates. This approach stands out for its computational efficiency. It only necessitates training one supplementary surrogate and avoids any data-specific assumptions. Furthermore, this method for work requires only the presence of the base model as a black box and its respective training data. The effectiveness of our approach is supported by experimental results. Using various time-series forecasting data, we found that our surrogate model-based technique delivers significantly more accurate confidence intervals. These techniques outperform both bootstrap-based and built-in methods in a medium-data regime. This superiority holds across a range of base model types, including a linear regression, ARIMA, gradient boosting and a neural network. |
|
| Learning Augmentation Policies from A Model Zoo for Time Series Forecasting | 2024-09-10 | ShowTime series forecasting models typically rely on a fixed-size training set and treat all data uniformly, which may not effectively capture the specific patterns present in more challenging training samples. To address this issue, we introduce AutoTSAug, a learnable data augmentation method based on reinforcement learning. Our approach begins with an empirical analysis to determine which parts of the training data should be augmented. Specifically, we identify the so-called marginal samples by considering the prediction diversity across a set of pretrained forecasting models. Next, we propose using variational masked autoencoders as the augmentation model and applying the REINFORCE algorithm to transform the marginal samples into new data. The goal of this generative model is not only to mimic the distribution of real data but also to reduce the variance of prediction errors across the model zoo. By augmenting the marginal samples with a learnable policy, AutoTSAug substantially improves forecasting performance, advancing the prior art in this field with minimal additional computational cost. |
|
| VE: Modeling Multivariate Time Series Correlation with Variate Embedding | 2024-09-10 | ShowMultivariate time series forecasting relies on accurately capturing the correlations among variates. Current channel-independent (CI) models and models with a CI final projection layer are unable to capture these dependencies. In this paper, we present the variate embedding (VE) pipeline, which learns a unique and consistent embedding for each variate and combines it with Mixture of Experts (MoE) and Low-Rank Adaptation (LoRA) techniques to enhance forecasting performance while controlling parameter size. The VE pipeline can be integrated into any model with a CI final projection layer to improve multivariate forecasting. The learned VE effectively groups variates with similar temporal patterns and separates those with low correlations. The effectiveness of the VE pipeline is demonstrated through extensive experiments on four widely-used datasets. The code is available at: \url{https://github.com/swang-song/VE}. |
|
| A statistical framework for analyzing shape in a time series of random geometric objects | 2024-09-09 | ShowWe introduce a new framework to analyze shape descriptors that capture the geometric features of an ensemble of point clouds. At the core of our approach is the point of view that the data arises as sampled recordings from a metric space-valued stochastic process, possibly of nonstationary nature, thereby integrating geometric data analysis into the realm of functional time series analysis. Our framework allows for natural incorporation of spatial-temporal dynamics, heterogeneous sampling, and the study of convergence rates. Further, we derive complete invariants for classes of metric space-valued stochastic processes in the spirit of Gromov, and relate these invariants to so-called ball volume processes. Under mild dependence conditions, a weak invariance principle in |
revised version |
| Symmetry constrained neural networks for detection and localization of damage in metal plates | 2024-09-09 | ShowThe present paper is concerned with deep learning techniques applied to detection and localization of damage in a thin aluminum plate. We used data generated on a tabletop apparatus by mounting to the plate four piezoelectric transducers, each of which took turn to generate a Lamb wave that then traversed the region of interest before being received by the remaining three sensors. On training a neural network to analyze time-series data of the material response, which displayed damage-reflective features whenever the plate guided waves interacted with a contact load, we achieved a model that detected with greater than 99% accuracy in addition to a model that localized with |
|
| Deep Convolutional Autoencoder for Assessment of Drive-Cycle Anomalies in Connected Vehicle Sensor Data | 2024-09-09 | ShowThis work investigates a practical and novel method for automated unsupervised fault detection in vehicles using a fully convolutional autoencoder. The results demonstrate the algorithm we developed can detect anomalies which correspond to powertrain faults by learning patterns in the multivariate time-series data of hybrid-electric vehicle powertrain sensors. Data was collected by engineers at Ford Motor Company from numerous sensors over several drive cycle variations. This study provides evidence of the anomaly detecting capability of our trained autoencoder and investigates the suitability of our autoencoder relative to other unsupervised methods for automatic fault detection in this data set. Preliminary results of testing the autoencoder on the powertrain sensor data indicate the data reconstruction approach availed by the autoencoder is a robust technique for identifying the abnormal sequences in the multivariate series. These results support that irregularities in hybrid-electric vehicles' powertrains are conveyed via sensor signals in the embedded electronic communication system, and therefore can be identified mechanistically with a trained algorithm. Additional unsupervised methods are tested and show the autoencoder performs better at fault detection than outlier detectors and other novel deep learning techniques. |
SSCI2...SSCI2022, 7 pages, 3 Tables, 3 Figures |
| Kernel-U-Net: Multivariate Time Series Forecasting using Custom Kernels | 2024-09-09 | ShowTime series forecasting task predicts future trends based on historical information. Transformer-based U-Net architectures, despite their success in medical image segmentation, have limitations in both expressiveness and computation efficiency in time series forecasting as evidenced in YFormer. To tackle these challenges, we introduce Kernel-U-Net, a flexible and kernel-customizable U-shape neural network architecture. The kernel-U-Net encoder compresses the input series into latent vectors, and its symmetric decoder subsequently expands these vectors into output series. Specifically, Kernel-U-Net separates the procedure of partitioning input time series into patches from kernel manipulation, thereby providing the convenience of customized executing kernels. Our method offers two primary advantages: 1) Flexibility in kernel customization to adapt to specific datasets; and 2) Enhanced computational efficiency, with the complexity of the Transformer layer reduced to linear. Experiments on seven real-world datasets, demonstrate that Kernel-U-Net's performance either exceeds or meets that of the existing state-of-the-art model in the majority of cases in channel-independent settings. The source code for Kernel-U-Net will be made publicly available for further research and application. |
|
| Predicting Electricity Consumption with Random Walks on Gaussian Processes | 2024-09-09 | ShowWe consider time-series forecasting problems where data is scarce, difficult to gather, or induces a prohibitive computational cost. As a first attempt, we focus on short-term electricity consumption in France, which is of strategic importance for energy suppliers and public stakeholders. The complexity of this problem and the many levels of geospatial granularity motivate the use of an ensemble of Gaussian Processes (GPs). Whilst GPs are remarkable predictors, they are computationally expensive to train, which calls for a frugal few-shot learning approach. By taking into account performance on GPs trained on a dataset and designing a random walk on these, we mitigate the training cost of our entire Bayesian decision-making procedure. We introduce our algorithm called \textsc{Domino} (ranDOM walk on gaussIaN prOcesses) and present numerical experiments to support its merits. |
6 pages |
| AnomalyCD: A benchmark for Earth anomaly change detection with high-resolution and time-series observations | 2024-09-09 | ShowVarious Earth anomalies have destroyed the stable, balanced state, resulting in fatalities and serious destruction of property. With the advantages of large-scale and precise observation, high-resolution remote sensing images have been widely used for anomaly monitoring and localization. Powered by the deep representation, the existing methods have achieved remarkable advances, primarily in classification and change detection techniques. However, labeled samples are difficult to acquire due to the low probability of anomaly occurrence, and the trained models are limited to fixed anomaly categories, which hinders the application for anomalies with few samples or unknown anomalies. In this paper, to tackle this problem, we propose the anomaly change detection (AnomalyCD) technique, which accepts time-series observations and learns to identify anomalous changes by learning from the historical normal change pattern. Compared to the existing techniques, AnomalyCD processes an unfixed number of time steps and can localize the various anomalies in a unified manner, without human supervision. To benchmark AnomalyCD, we constructed a high-resolution dataset with time-series images dedicated to various Earth anomalies (the AnomalyCDD dataset). AnomalyCDD contains high-resolution (from 0.15 to 2.39 m/pixel), time-series (from 3 to 7 time steps), and large-scale images (1927.93 km2 in total) collected globally Furthermore, we developed a zero-shot baseline model (AnomalyCDM), which implements the AnomalyCD technique by extracting a general representation from the segment anything model (SAM) and conducting temporal comparison to distinguish the anomalous changes from normal changes. AnomalyCDM is designed as a two-stage workflow to enhance the efficiency, and has the ability to process the unseen images directly, without retraining for each scene. |
remot...remote sensing benchmark |
| Optimizing VarLiNGAM for Scalable and Efficient Time Series Causal Discovery | 2024-09-09 | ShowCausal discovery is designed to identify causal relationships in data, a task that has become increasingly complex due to the computational demands of traditional methods such as VarLiNGAM, which combines Vector Autoregressive Model with Linear Non-Gaussian Acyclic Model for time series data. This study is dedicated to optimising causal discovery specifically for time series data, which is common in practical applications. Time series causal discovery is particularly challenging due to the need to account for temporal dependencies and potential time lag effects. By designing a specialised dataset generator and reducing the computational complexity of the VarLiNGAM model from ( O(m^3 \cdot n) ) to ( O(m^3 + m^2 \cdot n) ), this study significantly improves the feasibility of processing large datasets. The proposed methods have been validated on advanced computational platforms and tested across simulated, real-world, and large-scale datasets, showcasing enhanced efficiency and performance. The optimised algorithm achieved 7 to 13 times speedup compared with the original algorithm and around 4.5 times speedup compared with the GPU-accelerated version on large-scale datasets with feature sizes between 200 and 400. Our methods aim to push the boundaries of current causal discovery capabilities, making them more robust, scalable, and applicable to real-world scenarios, thus facilitating breakthroughs in various fields such as healthcare and finance. |
|
| GDFlow: Anomaly Detection with NCDE-based Normalizing Flow for Advanced Driver Assistance System | 2024-09-09 | ShowFor electric vehicles, the Adaptive Cruise Control (ACC) in Advanced Driver Assistance Systems (ADAS) is designed to assist braking based on driving conditions, road inclines, predefined deceleration strengths, and user braking patterns. However, the driving data collected during the development of ADAS are generally limited and lack diversity. This deficiency leads to late or aggressive braking for different users. Crucially, it is necessary to effectively identify anomalies, such as unexpected or inconsistent braking patterns in ADAS, especially given the challenge of working with unlabelled, limited, and noisy datasets from real-world electric vehicles. In order to tackle the aforementioned challenges in ADAS, we propose Graph Neural Controlled Differential Equation Normalizing Flow (GDFlow), a model that leverages Normalizing Flow (NF) with Neural Controlled Differential Equations (NCDE) to learn the distribution of normal driving patterns continuously. Compared to the traditional clustering or anomaly detection algorithms, our approach effectively captures the spatio-temporal information from different sensor data and more accurately models continuous changes in driving patterns. Additionally, we introduce a quantile-based maximum likelihood objective to improve the likelihood estimate of the normal data near the boundary of the distribution, enhancing the model's ability to distinguish between normal and anomalous patterns. We validate GDFlow using real-world electric vehicle driving data that we collected from Hyundai IONIQ5 and GV80EV, achieving state-of-the-art performance compared to six baselines across four dataset configurations of different vehicle types and drivers. Furthermore, our model outperforms the latest anomaly detection methods across four time series benchmark datasets. Our approach demonstrates superior efficiency in inference time compared to existing methods. |
|
| Boosting Certificate Robustness for Time Series Classification with Efficient Self-Ensemble | 2024-09-09 | ShowRecently, the issue of adversarial robustness in the time series domain has garnered significant attention. However, the available defense mechanisms remain limited, with adversarial training being the predominant approach, though it does not provide theoretical guarantees. Randomized Smoothing has emerged as a standout method due to its ability to certify a provable lower bound on robustness radius under |
6 fig...6 figures, 4 tables, 10 pages |
| TimelyGPT: Extrapolatable Transformer Pre-training for Long-term Time-Series Forecasting in Healthcare | 2024-09-08 | ShowLarge-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success in Natural Language Processing and Computer Vision domains. However, the development of PTMs on healthcare time-series data is lagging behind.This underscores the limitations of the existing transformer-based architectures, particularly their scalability to handle large-scale time series and ability to capture long-term temporal dependencies. In this study, we present Timely Generative Pre-trained Transformer (TimelyGPT). TimelyGPT employs an extrapolatable position (xPos) embedding to encode trend and periodic patterns into time-series representations. It also integrates recurrent attention and temporal convolution modules to effectively capture global-local temporal dependencies. We evaluated TimelyGPT on two large-scale healthcare time series datasets corresponding to continuous biosignals and irregularly-sampled time series, respectively. Our experiments show that during pre-training, TimelyGPT excels in learning time-series representations from continuously monitored biosignals and irregularly-sampled time series data commonly observed in longitudinal electronic health records (EHRs). In forecasting continuous biosignals, TimelyGPT achieves accurate extrapolation up to 6,000 timesteps of body temperature during the sleep stage transition, given a short look-up window (i.e., prompt) containing only 2,000 timesteps. For irregularly-sampled time series, TimelyGPT with a proposed time-specific inference demonstrates high top recall scores in predicting future diagnoses using early diagnostic records, effectively handling irregular intervals between clinical records. Together, we envision TimelyGPT to be useful in a broad spectrum of health domains, including long-term patient health state forecasting and patient risk trajectory prediction. |
17 pages |
| Exploring Fungal Morphology Simulation and Dynamic Light Containment from a Graphics Generation Perspective | 2024-09-08 | ShowFungal simulation and control are considered crucial techniques in Bio-Art creation. However, coding algorithms for reliable fungal simulations have posed significant challenges for artists. This study equates fungal morphology simulation to a two-dimensional graphic time-series generation problem. We propose a zero-coding, neural network-driven cellular automaton. Fungal spread patterns are learned through an image segmentation model and a time-series prediction model, which then supervise the training of neural network cells, enabling them to replicate real-world spreading behaviors. We further implemented dynamic containment of fungal boundaries with lasers. Synchronized with the automaton, the fungus successfully spreads into pre-designed complex shapes in reality. |
Siggr...Siggraph Asia 2024 Art Paper |
| Online Graph Topology Learning from Matrix-valued Time Series | 2024-09-08 | ShowThe focus is on the statistical analysis of matrix-valued time series, where data is collected over a network of sensors, typically at spatial locations, over time. Each sensor records a vector of features at each time point, creating a vectorial time series for each sensor. The goal is to identify the dependency structure among these sensors and represent it with a graph. When only one feature per sensor is observed, vector auto-regressive (VAR) models are commonly used to infer Granger causality, resulting in a causal graph. The first contribution extends VAR models to matrix-variate models for the purpose of graph learning. Additionally, two online procedures are proposed for both low and high dimensions, enabling rapid updates of coefficient estimates as new samples arrive. In the high-dimensional setting, a novel Lasso-type approach is introduced, and homotopy algorithms are developed for online learning. An adaptive tuning procedure for the regularization parameter is also provided. Given that the application of auto-regressive models to data typically requires detrending, which is not feasible in an online context, the proposed AR models are augmented by incorporating trend as an additional parameter, with a particular focus on periodic trends. The online algorithms are adapted to these augmented data models, allowing for simultaneous learning of the graph and trend from streaming samples. Numerical experiments using both synthetic and real data demonstrate the effectiveness of the proposed methods. |
|
| Learning Generative Models for Lumped Rainfall-Runoff Modeling | 2024-09-08 | ShowThis study presents a novel generative modeling approach to rainfall-runoff modeling, focusing on the synthesis of realistic daily catchment runoff time series in response to catchment-averaged climate forcing. Unlike traditional process-based lumped hydrologic models that depend on predefined sets of variables describing catchment physical properties, our approach uses a small number of latent variables to characterize runoff generation processes. These latent variables encapsulate the intrinsic properties of a catchment and can be inferred from catchment climate forcing and discharge data. By sampling from the latent variable space, the model generates runoff time series that closely resemble real-world observations. In this study, we trained the generative models using neural networks on data from over 3,000 global catchments and achieved prediction accuracies comparable to current deep learning models and various conventional lumped models, both within the catchments from the training set and from other regions worldwide. This suggests that the runoff generation process of catchments can be effectively captured by a low-dimensional latent representation. Yet, challenges such as equifinality and optimal determination of latent variables remain. Future research should focus on refining parameter estimation methods and exploring the physical meaning of these latent dimensions to improve model applicability and robustness. This generative approach offers a promising alternative for hydrological modeling that requires minimal assumptions about the physical processes of the catchment. |
|
| Path Development Network with Finite-dimensional Lie Group Representation | 2024-09-08 | ShowSignature, lying at the heart of rough path theory, is a central tool for analysing controlled differential equations driven by irregular paths. Recently it has also found extensive applications in machine learning and data science as a mathematically principled, universal feature that boosts the performance of deep learning-based models in sequential data tasks. It, nevertheless, suffers from the curse of dimensionality when paths are high-dimensional. We propose a novel, trainable path development layer, which exploits representations of sequential data through finite-dimensional Lie groups, thus resulting in dimension reduction. Its backpropagation algorithm is designed via optimization on manifolds. Our proposed layer, analogous to recurrent neural networks (RNN), possesses an explicit, simple recurrent unit that alleviates the gradient issues. Our layer demonstrates its strength in irregular time series modelling. Empirical results on a range of datasets show that the development layer consistently and significantly outperforms signature features on accuracy and dimensionality. The compact hybrid model (stacking one-layer LSTM with the development layer) achieves state-of-the-art against various RNN and continuous time series models. Our layer also enhances the performance of modelling dynamics constrained to Lie groups. Code is available at https://github.com/PDevNet/DevNet.git. |
|
| Efficient Rare Temporal Pattern Mining in Time Series | 2024-09-08 | ShowTime series data from various domains are increasing continuously. Extracting and analyzing the temporal patterns in these series can reveal significant insights. Temporal pattern mining (TPM) extends traditional pattern mining by incorporating event time intervals into extracted patterns, enhancing their expressiveness but increasing time and space complexities. One valuable type of temporal pattern is known as rare temporal patterns (RTPs), which occur rarely but with high confidence. There exist several challenges when mining rare temporal patterns. The support measure is set very low, leading to a further combinatorial explosion and potentially producing too many uninteresting patterns. Thus, an efficient approach to rare temporal pattern mining is needed. This paper introduces our Rare Temporal Pattern Mining from Time Series (RTPMfTS) method for discovering rare temporal patterns, featuring the following key contributions: (1) An end-to-end RTPMfTS process that takes time series data as input and yields rare temporal patterns as output. (2) An efficient Rare Temporal Pattern Mining (RTPM) algorithm that uses optimized data structures for quick event and pattern retrieval and utilizes effective pruning techniques for much faster mining. (3) A thorough experimental evaluation of RTPM, showing that RTPM outperforms the baseline in terms of runtime and memory usage. |
arXiv...arXiv admin note: substantial text overlap with arXiv:2306.10994 |
| NapTune: Efficient Model Tuning for Mood Classification using Previous Night's Sleep Measures along with Wearable Time-series | 2024-09-07 | ShowSleep is known to be a key factor in emotional regulation and overall mental health. In this study, we explore the integration of sleep measures from the previous night into wearable-based mood recognition. To this end, we propose NapTune, a novel prompt-tuning framework that utilizes sleep-related measures as additional inputs to a frozen pre-trained wearable time-series encoder by adding and training lightweight prompt parameters to each Transformer layer. Through rigorous empirical evaluation, we demonstrate that the inclusion of sleep data using NapTune not only improves mood recognition performance across different wearable time-series namely ECG, PPG, and EDA, but also makes it more sample-efficient. Our method demonstrates significant improvements over the best baselines and unimodal variants. Furthermore, we analyze the impact of adding sleep-related measures on recognizing different moods as well as the influence of individual sleep-related measures. |
Accep...Accepted at ICMI 2024 |
| A Multi-scenario Attention-based Generative Model for Personalized Blood Pressure Time Series Forecasting | 2024-09-07 | ShowContinuous blood pressure (BP) monitoring is essential for timely diagnosis and intervention in critical care settings. However, BP varies significantly across individuals, this inter-patient variability motivates the development of personalized models tailored to each patient's physiology. In this work, we propose a personalized BP forecasting model mainly using electrocardiogram (ECG) and photoplethysmogram (PPG) signals. This time-series model incorporates 2D representation learning to capture complex physiological relationships. Experiments are conducted on datasets collected from three diverse scenarios with BP measurements from 60 subjects total. Results demonstrate that the model achieves accurate and robust BP forecasts across scenarios within the Association for the Advancement of Medical Instrumentation (AAMI) standard criteria. This reliable early detection of abnormal fluctuations in BP is crucial for at-risk patients undergoing surgery or intensive care. The proposed model provides a valuable addition for continuous BP tracking to reduce mortality and improve prognosis. |
5 pages, 2 figures |
| Towards Hybrid Embedded Feature Selection and Classification Approach with Slim-TSF | 2024-09-06 | ShowTraditional solar flare forecasting approaches have mostly relied on physics-based or data-driven models using solar magnetograms, treating flare predictions as a point-in-time classification problem. This approach has limitations, particularly in capturing the evolving nature of solar activity. Recognizing the limitations of traditional flare forecasting approaches, our research aims to uncover hidden relationships and the evolutionary characteristics of solar flares and their source regions. Our previously proposed Sliding Window Multivariate Time Series Forest (Slim-TSF) has shown the feasibility of usage applied on multivariate time series data. A significant aspect of this study is the comparative analysis of our updated Slim-TSF framework against the original model outcomes. Preliminary findings indicate a notable improvement, with an average increase of 5% in both the True Skill Statistic (TSS) and Heidke Skill Score (HSS). This enhancement not only underscores the effectiveness of our refined methodology but also suggests that our systematic evaluation and feature selection approach can significantly advance the predictive accuracy of solar flare forecasting models. |
This ...This is a preprint accepted at the 26th International Conference on Big Data Analytics and Knowledge Discovery (DAWAK 2024) |
| Modeling, Inference, and Prediction in Mobility-Based Compartmental Models for Epidemiology | 2024-09-06 | ShowClassical compartmental models in epidemiology often assume a homogeneous population for simplicity, which neglects the inherent heterogeneity among individuals. This assumption frequently leads to inaccurate predictions when applied to real-world data. For example, evidence has shown that classical models overestimate the final pandemic size in the H1N1-2009 and COVID-19 outbreaks. To address this issue, we introduce individual mobility as a key factor in disease transmission and control. We characterize disease dynamics using mobility distribution functions for each compartment and propose a mobility-based compartmental model that incorporates population heterogeneity. Our results demonstrate that, for the same basic reproduction number, our mobility-based model predicts a smaller final pandemic size compared to the classical models, effectively addressing the common overestimation problem. Additionally, we infer mobility distributions from the time series of the infected population. We provide sufficient conditions for uniquely identifying the mobility distribution from a dataset and propose a machine-learning-based approach to learn mobility from both synthesized and real-world data. |
19 pages, 8 figures |
| Universal randomised signatures for generative time series modelling | 2024-09-06 | ShowRandomised signature has been proposed as a flexible and easily implementable alternative to the well-established path signature. In this article, we employ randomised signature to introduce a generative model for financial time series data in the spirit of reservoir computing. Specifically, we propose a novel Wasserstein-type distance based on discrete-time randomised signatures. This metric on the space of probability measures captures the distance between (conditional) distributions. Its use is justified by our novel universal approximation results for randomised signatures on the space of continuous functions taking the underlying path as an input. We then use our metric as the loss function in a non-adversarial generator model for synthetic time series data based on a reservoir neural stochastic differential equation. We compare the results of our model to benchmarks from the existing literature. |
33 pages |
| Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoT | 2024-09-06 | ShowThis paper presents the design of a hardware accelerator for Transformers, optimized for on-device time-series forecasting in AIoT systems. It integrates integer-only quantization and Quantization-Aware Training with optimized hardware designs to realize 6-bit and 4-bit quantized Transformer models, which achieved precision comparable to 8-bit quantized models from related research. Utilizing a complete implementation on an embedded FPGA (Xilinx Spartan-7 XC7S15), we examine the feasibility of deploying Transformer models on embedded IoT devices. This includes a thorough analysis of achievable precision, resource utilization, timing, power, and energy consumption for on-device inference. Our results indicate that while sufficient performance can be attained, the optimization process is not trivial. For instance, reducing the quantization bitwidth does not consistently result in decreased latency or energy consumption, underscoring the necessity of systematically exploring various optimization combinations. Compared to an 8-bit quantized Transformer model in related studies, our 4-bit quantized Transformer model increases test loss by only 0.63%, operates up to 132.33x faster, and consumes 48.19x less energy. |
7 pag...7 pages, 3 figures, 4 tables. The paper was accepted by 2024 IEEE Annual Congress on Artificial Intelligence of Things (IEEE AIoT) and got best paper award |
| Video alignment using unsupervised learning of local and global features | 2024-09-06 | ShowIn this paper, we tackle the problem of video alignment, the process of matching the frames of a pair of videos containing similar actions. The main challenge in video alignment is that accurate correspondence should be established despite the differences in the execution processes and appearances between the two videos. We introduce an unsupervised method for alignment that uses global and local features of the frames. In particular, we introduce effective features for each video frame by means of three machine vision tools: person detection, pose estimation, and VGG network. Then the features are processed and combined to construct a multidimensional time series that represent the video. The resulting time series are used to align videos of the same actions using a novel version of dynamic time warping named Diagonalized Dynamic Time Warping(DDTW). The main advantage of our approach is that no training is required, which makes it applicable for any new type of action without any need to collect training samples for it. Additionally, our approach can be used for framewise labeling of action phases in a dataset with only a few labeled videos. For evaluation, we considered video synchronization and phase classification tasks on the Penn action and subset of UCF101 datasets. Also, for an effective evaluation of the video synchronization task, we present a new metric called Enclosed Area Error(EAE). The results show that our method outperforms previous state-of-the-art methods, such as TCC, and other self-supervised and weakly supervised methods. |
11 pages, 6 figures |
| EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere | 2024-09-06 | ShowFull-body egocentric pose estimation from head and hand poses alone has become an active area of research to power articulate avatar representations on headset-based platforms. However, existing methods over-rely on the indoor motion-capture spaces in which datasets were recorded, while simultaneously assuming continuous joint motion capture and uniform body dimensions. We propose EgoPoser to overcome these limitations with four main contributions. 1) EgoPoser robustly models body pose from intermittent hand position and orientation tracking only when inside a headset's field of view. 2) We rethink input representations for headset-based ego-pose estimation and introduce a novel global motion decomposition method that predicts full-body pose independent of global positions. 3) We enhance pose estimation by capturing longer motion time series through an efficient SlowFast module design that maintains computational efficiency. 4) EgoPoser generalizes across various body shapes for different users. We experimentally evaluate our method and show that it outperforms state-of-the-art methods both qualitatively and quantitatively while maintaining a high inference speed of over 600fps. EgoPoser establishes a robust baseline for future work where full-body pose estimation no longer needs to rely on outside-in capture and can scale to large-scale and unseen environments. |
Accep...Accepted by ECCV 2024, Code: https://siplab.org/projects/EgoPoser |
| CryptoAnalytics: Cryptocoins Price Forecasting with Machine Learning Techniques | 2024-09-06 | ShowThis paper introduces CryptoAnalytics, a software toolkit for cryptocoins price forecasting with machine learning (ML) techniques. Cryptocoins are tradable digital assets exchanged for specific trading prices. While history has shown the extreme volatility of such trading prices, the ability to efficiently model and forecast the time series resulting from the exchange price volatility remains an open research challenge. Good results can been achieved with state-of-the-art ML techniques, including Gradient-Boosting Machines (GBMs) and Recurrent Neural Networks (RNNs). CryptoAnalytics is a software toolkit to easily train these models and make inference on up-to-date cryptocoin trading price data, with facilities to fetch datasets from one of the main leading aggregator websites, i.e., CoinMarketCap, train models and infer the future trends. This software is implemented in Python. It relies on PyTorch for the implementation of RNNs (LSTM and GRU), while for GBMs, it leverages on XgBoost, LightGBM and CatBoost. |
|
| Digital Ecosystem for FAIR Time Series Data Management in Environmental System Science | 2024-09-06 | ShowAddressing the challenges posed by climate change, biodiversity loss, and environmental pollution requires comprehensive monitoring and effective data management strategies that are applicable across various scales in environmental system science. This paper introduces a versatile and transferable digital ecosystem for managing time series data, designed to adhere to the FAIR principles (Findable, Accessible, Interoperable, and Reusable). The system is highly adaptable, cloud-ready, and suitable for deployment in a wide range of settings, from small-scale projects to large-scale monitoring initiatives. The ecosystem comprises three core components: the Sensor Management System (SMS) for detailed metadata registration and management; time.IO, a platform for efficient time series data storage, transfer, and real-time visualization; and the System for Automated Quality Control (SaQC), which ensures data integrity through real-time analysis and quality assurance. The modular architecture, combined with standardized protocols and interfaces, ensures that the ecosystem can be easily transferred and deployed across different environments and institutions. This approach enhances data accessibility for a broad spectrum of stakeholders, including researchers, policymakers, and the public, while fostering collaboration and advancing scientific research in environmental monitoring. |
|
| Liquid Resistance Liquid Capacitance Networks | 2024-09-06 | ShowWe introduce liquid-resistance liquid-capacitance neural networks (LRCs), a neural-ODE model which considerably improve the generalization, accuracy, and biological plausibility of electrical equivalent circuits (EECs), liquid time-constant networks (LTCs), and saturated liquid time-constant networks (STCs), respectively. We also introduce LRC units (LRCUs), as a very efficient and accurate gated RNN-model, which results from solving LRCs with an explicit Euler scheme using just one unfolding. We empirically show and formally prove that the liquid capacitance of LRCs considerably dampens the oscillations of LTCs and STCs, while at the same time dramatically increasing accuracy even for cheap solvers. We experimentally demonstrate that LRCs are a highly competitive alternative to popular neural ODEs and gated RNNs in terms of accuracy, efficiency, and interpretability, on classic time-series benchmarks and a complex autonomous-driving lane-keeping task. |
|
| An Efficient and Generalizable Symbolic Regression Method for Time Series Analysis | 2024-09-06 | ShowTime series analysis and prediction methods currently excel in quantitative analysis, offering accurate future predictions and diverse statistical indicators, but generally falling short in elucidating the underlying evolution patterns of time series. To gain a more comprehensive understanding and provide insightful explanations, we utilize symbolic regression techniques to derive explicit expressions for the non-linear dynamics in the evolution of time series variables. However, these techniques face challenges in computational efficiency and generalizability across diverse real-world time series data. To overcome these challenges, we propose \textbf{N}eural-\textbf{E}nhanced \textbf{Mo}nte-Carlo \textbf{T}ree \textbf{S}earch (NEMoTS) for time series. NEMoTS leverages the exploration-exploitation balance of Monte-Carlo Tree Search (MCTS), significantly reducing the search space in symbolic regression and improving expression quality. Furthermore, by integrating neural networks with MCTS, NEMoTS not only capitalizes on their superior fitting capabilities to concentrate on more pertinent operations post-search space reduction, but also replaces the complex and time-consuming simulation process, thereby substantially improving computational efficiency and generalizability in time series analysis. NEMoTS offers an efficient and comprehensive approach to time series analysis. Experiments with three real-world datasets demonstrate NEMoTS's significant superiority in performance, efficiency, reliability, and interpretability, making it well-suited for large-scale real-world time series data. |
|
| Latent Space Energy-based Neural ODEs | 2024-09-05 | ShowThis paper introduces a novel family of deep dynamical models designed to represent continuous-time sequence data. This family of models generates each data point in the time series by a neural emission model, which is a non-linear transformation of a latent state vector. The trajectory of the latent states is implicitly described by a neural ordinary differential equation (ODE), with the initial state following an informative prior distribution parameterized by an energy-based model. Furthermore, we can extend this model to disentangle dynamic states from underlying static factors of variation, represented as time-invariant variables in the latent space. We train the model using maximum likelihood estimation with Markov chain Monte Carlo (MCMC) in an end-to-end manner, without requiring additional assisting components such as an inference network. Our experiments on oscillating systems, videos and real-world state sequences (MuJoCo) illustrate that ODEs with the learnable energy-based prior outperform existing counterparts, and can generalize to new dynamic parameterization, enabling long-horizon predictions. |
|
| AI forecasting of higher-order wave modes of spinning binary black hole mergers | 2024-09-05 | ShowWe present a physics-inspired transformer model that predicts the non-linear dynamics of higher-order wave modes emitted by quasi-circular, spinning, non-precessing binary black hole mergers. The model forecasts the waveform evolution from the pre-merger phase through the ringdown, starting with an input time-series spanning $ t \in [-5000\textrm{M}, -100\textrm{M}) $. The merger event, defined as the peak amplitude of waveforms that include the $l = |
m |
| Practical Forecasting of Cryptocoins Timeseries using Correlation Patterns | 2024-09-05 | ShowCryptocoins (i.e., Bitcoin, Ether, Litecoin) are tradable digital assets. Ownerships of cryptocoins are registered on distributed ledgers (i.e., blockchains). Secure encryption techniques guarantee the security of the transactions (transfers of coins among owners), registered into the ledger. Cryptocoins are exchanged for specific trading prices. The extreme volatility of such trading prices across all different sets of crypto-assets remains undisputed. However, the relations between the trading prices across different cryptocoins remains largely unexplored. Major coin exchanges indicate trend correlation to advise for sells or buys. However, price correlations remain largely unexplored. We shed some light on the trend correlations across a large variety of cryptocoins, by investigating their coin/price correlation trends over the past two years. We study the causality between the trends, and exploit the derived correlations to understand the accuracy of state-of-the-art forecasting techniques for time series modeling (e.g., GBMs, LSTM and GRU) of correlated cryptocoins. Our evaluation shows (i) strong correlation patterns between the most traded coins (e.g., Bitcoin and Ether) and other types of cryptocurrencies, and (ii) state-of-the-art time series forecasting algorithms can be used to forecast cryptocoins price trends. We released datasets and code to reproduce our analysis to the research community. |
|
| A method to benchmark high-dimensional process drift detection | 2024-09-05 | ShowProcess curves are multi-variate finite time series data coming from manufacturing processes. This paper studies machine learning methods for drifts of process curves. A theoretic framework to synthetically generate process curves in a controlled way is introduced in order to benchmark machine learning algorithms for process drift detection. A evaluation score, called the temporal area under the curve, is introduced, which allows to quantify how well machine learning models unveil curves belonging to drift segments. Finally, a benchmark study comparing popular machine learning approaches on synthetic data generated with the introduced framework shown. |
|
| VFLGAN-TS: Vertical Federated Learning-based Generative Adversarial Networks for Publication of Vertically Partitioned Time-Series Data | 2024-09-05 | ShowIn the current artificial intelligence (AI) era, the scale and quality of the dataset play a crucial role in training a high-quality AI model. However, often original data cannot be shared due to privacy concerns and regulations. A potential solution is to release a synthetic dataset with a similar distribution to the private dataset. Nevertheless, in some scenarios, the attributes required to train an AI model are distributed among different parties, and the parties cannot share the local data for synthetic data construction due to privacy regulations. In PETS 2024, we recently introduced the first Vertical Federated Learning-based Generative Adversarial Network (VFLGAN) for publishing vertically partitioned static data. However, VFLGAN cannot effectively handle time-series data, presenting both temporal and attribute dimensions. In this article, we proposed VFLGAN-TS, which combines the ideas of attribute discriminator and vertical federated learning to generate synthetic time-series data in the vertically partitioned scenario. The performance of VFLGAN-TS is close to that of its counterpart, which is trained in a centralized manner and represents the upper limit for VFLGAN-TS. To further protect privacy, we apply a Gaussian mechanism to make VFLGAN-TS satisfy an |
|
| TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack | 2024-09-05 | ShowRecent years have witnessed the success of recurrent neural network (RNN) models in time series classification (TSC). However, neural networks (NNs) are vulnerable to adversarial samples, which cause real-life adversarial attacks that undermine the robustness of AI models. To date, most existing attacks target at feed-forward NNs and image recognition tasks, but they cannot perform well on RNN-based TSC. This is due to the cyclical computation of RNN, which prevents direct model differentiation. In addition, the high visual sensitivity of time series to perturbations also poses challenges to local objective optimization of adversarial samples. In this paper, we propose an efficient method called TSFool to craft highly-imperceptible adversarial time series for RNN-based TSC. The core idea is a new global optimization objective known as "Camouflage Coefficient" that captures the imperceptibility of adversarial samples from the class distribution. Based on this, we reduce the adversarial attack problem to a multi-objective optimization problem that enhances the perturbation quality. Furthermore, to speed up the optimization process, we propose to use a representation model for RNN to capture deeply embedded vulnerable samples whose features deviate from the latent manifold. Experiments on 11 UCR and UEA datasets showcase that TSFool significantly outperforms six white-box and three black-box benchmark attacks in terms of effectiveness, efficiency and imperceptibility from various perspectives including standard measure, human study and real-world defense. |
27th ...27th European Conference on Artificial Intelligence (ECAI'24) |
| Interpretable mixture of experts for time series prediction under recurrent and non-recurrent conditions | 2024-09-05 | ShowNon-recurrent conditions caused by incidents are different from recurrent conditions that follow periodic patterns. Existing traffic speed prediction studies are incident-agnostic and use one single model to learn all possible patterns from these drastically diverse conditions. This study proposes a novel Mixture of Experts (MoE) model to improve traffic speed prediction under two separate conditions, recurrent and non-recurrent (i.e., with and without incidents). The MoE leverages separate recurrent and non-recurrent expert models (Temporal Fusion Transformers) to capture the distinct patterns of each traffic condition. Additionally, we propose a training pipeline for non-recurrent models to remedy the limited data issues. To train our model, multi-source datasets, including traffic speed, incident reports, and weather data, are integrated and processed to be informative features. Evaluations on a real road network demonstrate that the MoE achieves lower errors compared to other benchmark algorithms. The model predictions are interpreted in terms of temporal dependencies and variable importance in each condition separately to shed light on the differences between recurrent and non-recurrent conditions. |
|
| Application Research On Real-Time Perception Of Device Performance Status | 2024-09-05 | ShowIn order to accurately identify the performance status of mobile devices and finely adjust the user experience, a real-time performance perception evaluation method based on TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) combined with entropy weighting method and time series model construction was studied. After collecting the performance characteristics of various mobile devices, the device performance profile was fitted by using PCA (principal component analysis) dimensionality reduction and feature engineering methods such as descriptive time series analysis. The ability of performance features and profiles to describe the real-time performance status of devices was understood and studied by applying the TOPSIS method and multi-level weighting processing. A time series model was constructed for the feature set under objective weighting, and multiple sensitivity (real-time, short-term, long-term) performance status perception results were provided to obtain real-time performance evaluation data and long-term stable performance prediction data. Finally, by configuring dynamic AB experiments and overlaying fine-grained power reduction strategies, the usability of the method was verified, and the accuracy of device performance status identification and prediction was compared with the performance of the profile features including dimensionality reduction time series modeling, TOPSIS method and entropy weighting method, subjective weighting, HMA method. The results show that accurate real-time performance perception results can greatly enhance business value, and this research has application effectiveness and certain forward-looking significance. |
|
| Cointegration test in time series analysis by global optimisation | 2024-09-05 | ShowIn this paper, we provide an optimisation approach motivated by the Blind Source Separation, or also known as Independent Component Analysis, for cointegration between financial time series. Two methods for cointegration tests are introduced, namely decorrelation for the bivariate case and maximisation of nongaussianity for higher-dimensions. The advantages of our methods, especially the better performances in limited sample size, enable a wider range of application and accessibility for researchers and practitioners to identify cointegrating relationships. |
|
| Prediction of COPD Using Machine Learning, Clinical Summary Notes, and Vital Signs | 2024-09-05 | ShowChronic obstructive pulmonary disease (COPD) is a chronic inflammatory lung disease that causes obstructed airflow from the lungs. In the United States, more than 15.7 million Americans have been diagnosed with COPD, with 96% of individuals living with at least one other chronic health condition. It is the 4th leading cause of death in the country. Over 2.2 million patients are admitted to hospitals annually due to COPD exacerbations. Monitoring and predicting patient exacerbations on-time could save their life. This paper presents two different predictive models to predict COPD exacerbation using AI and natural language processing (NLP) approaches. These models use respiration summary notes, symptoms, and vital signs. To train and test these models, data records containing physiologic signals and vital signs time series were used. These records were captured from patient monitors and comprehensive clinical data obtained from hospital medical information systems for tens of thousands of Intensive Care Unit (ICU) patients. We achieved an area under the Receiver operating characteristic (ROC) curve of 0.82 in detection and prediction of COPD exacerbation. |
11 pages, 5 figures |
| Explanation Space: A New Perspective into Time Series Interpretability | 2024-09-05 | ShowHuman understandable explanation of deep learning models is necessary for many critical and sensitive applications. Unlike image or tabular data where the importance of each input feature (for the classifier's decision) can be directly projected into the input, time series distinguishable features (e.g. dominant frequency) are often hard to manifest in time domain for a user to easily understand. Moreover, most explanation methods require a baseline value as an indication of the absence of any feature. However, the notion of lack of feature, which is often defined as black pixels for vision tasks or zero/mean values for tabular data, is not well-defined in time series. Despite the adoption of explainable AI methods (XAI) from tabular and vision domain into time series domain, these differences limit the application of these XAI methods in practice. In this paper, we propose a simple yet effective method that allows a model originally trained on time domain to be interpreted in other explanation spaces using existing methods. We suggest four explanation spaces that each can potentially alleviate these issues in certain types of time series. Our method can be readily adopted in existing platforms without any change to trained models or XAI methods. The code is available at https://github.com/shrezaei/TS-X-spaces. |
|
| Non-stationary and Sparsely-correlated Multi-output Gaussian Process with Spike-and-Slab Prior | 2024-09-05 | ShowMulti-output Gaussian process (MGP) is commonly used as a transfer learning method to leverage information among multiple outputs. A key advantage of MGP is providing uncertainty quantification for prediction, which is highly important for subsequent decision-making tasks. However, traditional MGP may not be sufficiently flexible to handle multivariate data with dynamic characteristics, particularly when dealing with complex temporal correlations. Additionally, since some outputs may lack correlation, transferring information among them may lead to negative transfer. To address these issues, this study proposes a non-stationary MGP model that can capture both the dynamic and sparse correlation among outputs. Specifically, the covariance functions of MGP are constructed using convolutions of time-varying kernel functions. Then a dynamic spike-and-slab prior is placed on correlation parameters to automatically decide which sources are informative to the target output in the training process. An expectation-maximization (EM) algorithm is proposed for efficient model fitting. Both numerical studies and a real case demonstrate its efficacy in capturing dynamic and sparse correlation structure and mitigating negative transfer for high-dimensional time-series data. Finally, a mountain-car reinforcement learning case highlights its potential application in decision making problems. |
|
| VECA: Reliable and Confidential Resource Clustering for Volunteer Edge-Cloud Computing | 2024-09-04 | ShowVolunteer Edge-Cloud (VEC) computing has a significant potential to support scientific workflows in user communities contributing volunteer edge nodes. However, managing heterogeneous and intermittent resources to support machine/deep learning (ML/DL) based workflows poses challenges in resource governance for reliability, and confidentiality for model/data privacy protection. There is a need for approaches to handle the volatility of volunteer edge node availability, and also to scale the confidential data-intensive workflow execution across a large number of VEC nodes. In this paper, we present VECA, a reliable and confidential VEC resource clustering solution featuring three-fold methods tailored for executing ML/DL-based scientific workflows on VEC resources. Firstly, a capacity-based clustering approach enhances system reliability and minimizes VEC node search latency. Secondly, a novel two-phase, globally distributed scheduling scheme optimizes job allocation based on node attributes and using time-series-based Recurrent Neural Networks. Lastly, the integration of confidential computing ensures privacy preservation of the scientific workflows, where model and data information are not shared with VEC resources providers. We evaluate VECA in a Function-as-a-Service (FaaS) cloud testbed that features OpenFaaS and MicroK8S to support two ML/DL-based scientific workflows viz., G2P-Deep (bioinformatics) and PAS-ML (health informatics). Results from tested experiments demonstrate that our proposed VECA approach outperforms state-of-the-art methods; especially VECA exhibits a two-fold reduction in VEC node search latency and over 20% improvement in productivity rates following execution failures compared to the next best method. |
Accep...Accepted - IC2E 2024 Conference |
| Look Into the LITE in Deep Learning for Time Series Classification | 2024-09-04 | ShowDeep learning models have been shown to be a powerful solution for Time Series Classification (TSC). State-of-the-art architectures, while producing promising results on the UCR and the UEA archives , present a high number of trainable parameters. This can lead to long training with high CO2 emission, power consumption and possible increase in the number of FLoating-point Operation Per Second (FLOPS). In this paper, we present a new architecture for TSC, the Light Inception with boosTing tEchnique (LITE) with only 2.34% of the number of parameters of the state-of-the-art InceptionTime model, while preserving performance. This architecture, with only 9, 814 trainable parameters due to the usage of DepthWise Separable Convolutions (DWSC), is boosted by three techniques: multiplexing, custom filters, and dilated convolution. The LITE architecture, trained on the UCR, is 2.78 times faster than InceptionTime and consumes 2.79 times less CO2 and power. To evaluate the performance of the proposed architecture on multivariate time series data, we adapt LITE to handle multivariate time series, we call this version LITEMV. To bring theory into application, we also conducted experiments using LITEMV on multivariate time series representing human rehabilitation movements, showing that LITEMV not only is the most efficient model but also the best performing for this application on the Kimore dataset, a skeleton based human rehabilitation exercises dataset. Moreover, to address the interpretability of LITEMV, we present a study using Class Activation Maps to understand the classification decision taken by the model during evaluation. |
|
| Variational Mode Decomposition and Linear Embeddings are What You Need For Time-Series Forecasting | 2024-09-04 | ShowTime-series forecasting often faces challenges due to data volatility, which can lead to inaccurate predictions. Variational Mode Decomposition (VMD) has emerged as a promising technique to mitigate volatility by decomposing data into distinct modes, thereby enhancing forecast accuracy. In this study, we integrate VMD with linear models to develop a robust forecasting framework. Our approach is evaluated on 13 diverse datasets, including ETTm2, WindTurbine, M4, and 10 air quality datasets from various Southeast Asian cities. The effectiveness of the VMD strategy is assessed by comparing Root Mean Squared Error (RMSE) values from models utilizing VMD against those without it. Additionally, we benchmark linear-based models against well-known neural network architectures such as LSTM, Bidirectional LSTM, and RNN. The results demonstrate a significant reduction in RMSE across nearly all models following VMD application. Notably, the Linear + VMD model achieved the lowest average RMSE in univariate forecasting at 0.619. In multivariate forecasting, the DLinear + VMD model consistently outperformed others, attaining the lowest RMSE across all datasets with an average of 0.019. These findings underscore the effectiveness of combining VMD with linear models for superior time-series forecasting. |
For a...For associated repository, see https://github.com/Espalemit/VMD-With-LTSF-Linear.git |
| Neural Networks with LSTM and GRU in Modeling Active Fires in the Amazon | 2024-09-04 | ShowThis study presents a comprehensive methodology for modeling and forecasting the historical time series of fire spots detected by the AQUA_M-T satellite in the Amazon, Brazil. The approach utilizes a mixed Recurrent Neural Network (RNN) model, combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures to predict monthly accumulations of daily detected fire spots. A summary of the data revealed a consistent seasonality over time, with annual maximum and minimum fire spot values tending to repeat at the same periods each year. The primary objective is to verify whether the forecasts capture this inherent seasonality through rigorous statistical analysis. The methodology involved careful data preparation, model configuration, and training using cross-validation with two seeds, ensuring that the data generalizes well to the test and validation sets, and confirming the convergence of the model parameters. The results indicate that the mixed LSTM and GRU model offers improved accuracy in forecasting 12 months ahead, demonstrating its effectiveness in capturing complex temporal patterns and modeling the observed time series. This research significantly contributes to the application of deep learning techniques in environmental monitoring, specifically in fire spot forecasting. In addition to improving forecast accuracy, the proposed approach highlights the potential for adaptation to other time series forecasting challenges, opening new avenues for research and development in machine learning and natural phenomenon prediction. Keywords: Time Series Forecasting, Recurrent Neural Networks, Deep Learning. |
16 pa...16 pages, in Portuguese language, 24 figures |
| PUB: Plot Understanding Benchmark and Dataset for Evaluating Large Language Models on Synthetic Visual Data Interpretation | 2024-09-04 | ShowThe ability of large language models (LLMs) to interpret visual representations of data is crucial for advancing their application in data analysis and decision-making processes. This paper presents a novel synthetic dataset designed to evaluate the proficiency of LLMs in interpreting various forms of data visualizations, including plots like time series, histograms, violins, boxplots, and clusters. Our dataset is generated using controlled parameters to ensure comprehensive coverage of potential real-world scenarios. We employ multimodal text prompts with questions related to visual data in images to benchmark several state-of-the-art models like ChatGPT or Gemini, assessing their understanding and interpretative accuracy. To ensure data integrity, our benchmark dataset is generated automatically, making it entirely new and free from prior exposure to the models being tested. This strategy allows us to evaluate the models' ability to truly interpret and understand the data, eliminating possibility of pre-learned responses, and allowing for an unbiased evaluation of the models' capabilities. We also introduce quantitative metrics to assess the performance of the models, providing a robust and comprehensive evaluation tool. Benchmarking several state-of-the-art LLMs with this dataset reveals varying degrees of success, highlighting specific strengths and weaknesses in interpreting diverse types of visual data. The results provide valuable insights into the current capabilities of LLMs and identify key areas for improvement. This work establishes a foundational benchmark for future research and development aimed at enhancing the visual interpretative abilities of language models. In the future, improved LLMs with robust visual interpretation skills can significantly aid in automated data analysis, scientific research, educational tools, and business intelligence applications. |
|
| In the Search for Optimal Multi-view Learning Models for Crop Classification with Global Remote Sensing Data | 2024-09-04 | ShowStudying and analyzing cropland is a difficult task due to its dynamic and heterogeneous growth behavior. Usually, diverse data sources can be collected for its estimation. Although deep learning models have proven to excel in the crop classification task, they face substantial challenges when dealing with multiple inputs, named Multi-View Learning (MVL). The methods used in the MVL scenario can be structured based on the encoder architecture, the fusion strategy, and the optimization technique. The literature has primarily focused on using specific encoder architectures for local regions, lacking a deeper exploration of other components in the MVL methodology. In contrast, we investigate the simultaneous selection of the fusion strategy and encoder architecture, assessing global-scale cropland and crop-type classifications. We use a range of five fusion strategies (Input, Feature, Decision, Ensemble, Hybrid) and five temporal encoders (LSTM, GRU, TempCNN, TAE, L-TAE) as possible configurations in the MVL method. We use the CropHarvest dataset for validation, which provides optical, radar, weather time series, and topographic information as input data. We found that in scenarios with a limited number of labeled samples, a unique configuration is insufficient for all the cases. Instead, a specialized combination should be meticulously sought, including an encoder and fusion strategy. To streamline this search process, we suggest identifying the optimal encoder architecture tailored for a particular fusion strategy, and then determining the most suitable fusion strategy for the classification task. We provide a methodological framework for researchers exploring crop classification through an MVL methodology. |
submitted to journal |
| Test-time data augmentation: improving predictions of recurrent neural network models of composites | 2024-09-04 | ShowRecurrent Neural Networks (RNNs) have emerged as an interesting alternative to conventional material modeling approaches, particularly for nonlinear path dependent materials. Remarkable computational enhancements are obtained using RNNs compared to classical approaches such as the computational homogenization method. However, RNN predictive errors accumulate, leading to issues when predicting temporal dependencies in time series data. This study aims to address and mitigate inaccuracies induced by neural networks in predicting path dependent plastic deformations of short fiber reinforced composite materials. We propose using an approach of Test Time data Augmentation (TTA), which, to the best of the authors knowledge, is previously untested in the context of RNNs. The method is based on augmenting the input test data using random rotations and subsequently rotating back the predicted output signal. By aggregating the back rotated predictions, a more accurate prediction compared to individual predictions is obtained. Our analysis also demonstrates improved shape consistency between the prediction and the target pseudo time signal. Additionally, this method provides an uncertainty estimation which correlates with the absolute prediction error. The TTA approach is reproducible with different randomly generated data augmentations, establishing a promising framework for optimizing predictions of deep learning models. We believe there are broader implications of the proposed method for various fields reliant on accurate predictive data driven modeling. |
|
| TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model | 2024-09-03 | ShowWith recent advances in building foundation models for texts and video data, there is a surge of interest in foundation models for time series. A family of models have been developed, utilizing a temporal auto-regressive generative Transformer architecture, whose effectiveness has been proven in Large Language Models. While the empirical results are promising, almost all existing time series foundation models have only been tested on well-curated ``benchmark'' datasets very similar to texts. However, real-world time series exhibit unique challenges, such as variable channel sizes across domains, missing values, and varying signal sampling intervals due to the multi-resolution nature of real-world data. Additionally, the uni-directional nature of temporally auto-regressive decoding limits the incorporation of domain knowledge, such as physical laws expressed as partial differential equations (PDEs). To address these challenges, we introduce the Time Diffusion Transformer (TimeDiT), a general foundation model for time series that employs a denoising diffusion paradigm instead of temporal auto-regressive generation. TimeDiT leverages the Transformer architecture to capture temporal dependencies and employs diffusion processes to generate high-quality candidate samples without imposing stringent assumptions on the target distribution via novel masking schemes and a channel alignment strategy. Furthermore, we propose a finetuning-free model editing strategy that allows the seamless integration of external knowledge during the sampling process without updating any model parameters. Extensive experiments conducted on a varity of tasks such as forecasting, imputation, and anomaly detection, demonstrate the effectiveness of TimeDiT. |
23 Pa...23 Pages, 6 Figures, 11 Tables. First present at ICML 2024 Workshop on Foundation Models in the Wild |
| Delay Parameter Selection in Permutation Entropy Using Topological Data Analysis | 2024-09-03 | ShowPermutation Entropy (PE) is a powerful tool for quantifying the complexity of a signal which includes measuring the regularity of a time series. Additionally, outside of entropy and information theory, permutations have recently been leveraged as a graph representation, which opens the door for graph theory tools and analysis. Despite the successful application of permutations in a variety of scientific domains, permutations requires a judicious choice of the delay parameter |
Added...Added Max M. Chumley as a co-author. Added delay embedding plots that show how sublevel persistence unfolds example attractors. Added time series forecasting results obtained using parameters selected by our method for two nonlinear systems. Removed SW1PerS results for finding the delay since they do not generalize to non-periodic signals |
| Improving the Prediction of Individual Engagement in Recommendations Using Cognitive Models | 2024-09-03 | ShowFor public health programs with limited resources, the ability to predict how behaviors change over time and in response to interventions is crucial for deciding when and to whom interventions should be allocated. Using data from a real-world maternal health program, we demonstrate how a cognitive model based on Instance-Based Learning (IBL) Theory can augment existing purely computational approaches. Our findings show that, compared to general time-series forecasters (e.g., LSTMs), IBL models, which reflect human decision-making processes, better predict the dynamics of individuals' states. Additionally, IBL provides estimates of the volatility in individuals' states and their sensitivity to interventions, which can improve the efficiency of training of other time series models. |
|
| Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting | 2024-09-03 | ShowSpatiotemporal time series forecasting plays a key role in a wide range of real-world applications. While significant progress has been made in this area, fully capturing and leveraging spatiotemporal heterogeneity remains a fundamental challenge. Therefore, we propose a novel Heterogeneity-Informed Meta-Parameter Learning scheme. Specifically, our approach implicitly captures spatiotemporal heterogeneity through learning spatial and temporal embeddings, which can be viewed as a clustering process. Then, a novel spatiotemporal meta-parameter learning paradigm is proposed to learn spatiotemporal-specific parameters from meta-parameter pools, which is informed by the captured heterogeneity. Based on these ideas, we develop a Heterogeneity-Informed Spatiotemporal Meta-Network (HimNet) for spatiotemporal time series forecasting. Extensive experiments on five widely-used benchmarks demonstrate our method achieves state-of-the-art performance while exhibiting superior interpretability. Our code is available at https://github.com/XDZhelheim/HimNet. |
Publi...Published in KDD'24 Research Track |
| Towards Explainable Traffic Flow Prediction with Large Language Models | 2024-09-03 | ShowTraffic forecasting is crucial for intelligent transportation systems. It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data. However, recent deep-learning architectures require intricate model designs and lack an intuitive understanding of the mapping from input data to predicted results. Achieving both accuracy and explainability in traffic prediction models remains a challenge due to the complexity of traffic data and the inherent opacity of deep learning models. To tackle these challenges, we propose a Traffic flow Prediction model based on Large Language Models (LLMs) to generate explainable traffic predictions, named xTP-LLM. By transferring multi-modal traffic data into natural language descriptions, xTP-LLM captures complex time-series patterns and external factors from comprehensive traffic data. The LLM framework is fine-tuned using language-based instructions to align with spatial-temporal traffic flow data. Empirically, xTP-LLM shows competitive accuracy compared with deep learning baselines, while providing an intuitive and reliable explanation for predictions. This paper contributes to advancing explainable traffic prediction models and lays a foundation for future exploration of LLM applications in transportation. To the best of our knowledge, this is the first study to use LLM for explainable prediction of traffic flows. |
31pages, 16 figures |
| Interpreting Outliers in Time Series Data through Decoding Autoencoder | 2024-09-03 | ShowOutlier detection is a crucial analytical tool in various fields. In critical systems like manufacturing, malfunctioning outlier detection can be costly and safety-critical. Therefore, there is a significant need for explainable artificial intelligence (XAI) when deploying opaque models in such environments. This study focuses on manufacturing time series data from a German automotive supply industry. We utilize autoencoders to compress the entire time series and then apply anomaly detection techniques to its latent features. For outlier interpretation, we (i) adopt widely used XAI techniques to the autoencoder's encoder. Additionally, (ii) we propose AEE, Aggregated Explanatory Ensemble, a novel approach that fuses explanations of multiple XAI techniques into a single, more expressive interpretation. For evaluation of explanations, (iii) we propose a technique to measure the quality of encoder explanations quantitatively. Furthermore, we qualitatively assess the effectiveness of outlier explanations with domain expertise. |
14 pa...14 pages, 8 figures, accepted at TempXAI @ ECML-PKDD |
| TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Models | 2024-09-03 | ShowTime series anomaly detection (TSAD) has gained significant attention due to its real-world applications to improve the stability of modern software systems. However, there is no effective way to verify whether they can meet the requirements for real-world deployment. Firstly, current algorithms typically train a specific model for each time series. Maintaining such many models is impractical in a large-scale system with tens of thousands of curves. The performance of using merely one unified model to detect anomalies remains unknown. Secondly, most TSAD models are trained on the historical part of a time series and are tested on its future segment. In distributed systems, however, there are frequent system deployments and upgrades, with new, previously unseen time series emerging daily. The performance of testing newly incoming unseen time series on current TSAD algorithms remains unknown. Lastly, the assumptions of the evaluation metrics in existing benchmarks are far from practical demands. To solve the above-mentioned problems, we propose an industrial-grade benchmark TimeSeriesBench. We assess the performance of existing algorithms across more than 168 evaluation settings and provide comprehensive analysis for the future design of anomaly detection algorithms. An industrial dataset is also released along with TimeSeriesBench. |
Accepted by ISSRE'24 |
| Hybridization of Persistent Homology with Neural Networks for Time-Series Prediction: A Case Study in Wave Height | 2024-09-03 | ShowTime-series prediction is an active area of research across various fields, often challenged by the fluctuating influence of short-term and long-term factors. In this study, we introduce a feature engineering method that enhances the predictive performance of neural network models. Specifically, we leverage computational topology techniques to derive valuable topological features from input data, boosting the predictive accuracy of our models. Our focus is on predicting wave heights, utilizing models based on topological features within feedforward neural networks (FNNs), recurrent neural networks (RNNs), long short-term memory networks (LSTM), and RNNs with gated recurrent units (GRU). For time-ahead predictions, the enhancements in |
|
| Optimal training of finitely-sampled quantum reservoir computers for forecasting of chaotic dynamics | 2024-09-02 | ShowIn the current Noisy Intermediate Scale Quantum (NISQ) era, the presence of noise deteriorates the performance of quantum computing algorithms. Quantum Reservoir Computing (QRC) is a type of Quantum Machine Learning algorithm, which, however, can benefit from different types of tuned noise. In this paper, we analyse the effect that finite-sampling noise has on the chaotic time-series prediction capabilities of QRC and Recurrence-free Quantum Reservoir Computing (RF-QRC). First, we show that, even without a recurrent loop, RF-QRC contains temporal information about previous reservoir states using leaky integrated neurons. This makes RF-QRC different from Quantum Extreme Learning Machines (QELM). Second, we show that finite sampling noise degrades the prediction capabilities of both QRC and RF-QRC while affecting QRC more due to the propagation of noise. Third, we optimize the training of the finite-sampled quantum reservoir computing framework using two methods: (a) Singular Value Decomposition (SVD) applied to the data matrix containing noisy reservoir activation states; and (b) data-filtering techniques to remove the high-frequencies from the noisy reservoir activation states. We show that denoising reservoir activation states improve the signal-to-noise ratios with smaller training loss. Finally, we demonstrate that the training and denoising of the noisy reservoir activation signals in RF-QRC are highly parallelizable on multiple Quantum Processing Units (QPUs) as compared to the QRC architecture with recurrent connections. The analyses are numerically showcased on prototypical chaotic dynamical systems with relevance to turbulence. This work opens opportunities for using quantum reservoir computing with finite samples for time-series forecasting on near-term quantum hardware. |
11 pages, 14 figures |
| Correlating Time Series with Interpretable Convolutional Kernels | 2024-09-02 | ShowThis study addresses the problem of convolutional kernel learning in univariate, multivariate, and multidimensional time series data, which is crucial for interpreting temporal patterns in time series and supporting downstream machine learning tasks. First, we propose formulating convolutional kernel learning for univariate time series as a sparse regression problem with a non-negative constraint, leveraging the properties of circular convolution and circulant matrices. Second, to generalize this approach to multivariate and multidimensional time series data, we use tensor computations, reformulating the convolutional kernel learning problem in the form of tensors. This is further converted into a standard sparse regression problem through vectorization and tensor unfolding operations. In the proposed methodology, the optimization problem is addressed using the existing non-negative subspace pursuit method, enabling the convolutional kernel to capture temporal correlations and patterns. To evaluate the proposed model, we apply it to several real-world time series datasets. On the multidimensional rideshare and taxi trip data from New York City and Chicago, the convolutional kernels reveal interpretable local correlations and cyclical patterns, such as weekly seasonality. In the context of multidimensional fluid flow data, both local and nonlocal correlations captured by the convolutional kernels can reinforce tensor factorization, leading to performance improvements in fluid flow reconstruction tasks. Thus, this study lays an insightful foundation for automatically learning convolutional kernels from time series data, with an emphasis on interpretability through sparsity and non-negativity constraints. |
11 pages, 7 figures |
| A Financial Time Series Denoiser Based on Diffusion Model | 2024-09-02 | ShowFinancial time series often exhibit low signal-to-noise ratio, posing significant challenges for accurate data interpretation and prediction and ultimately decision making. Generative models have gained attention as powerful tools for simulating and predicting intricate data patterns, with the diffusion model emerging as a particularly effective method. This paper introduces a novel approach utilizing the diffusion model as a denoiser for financial time series in order to improve data predictability and trading performance. By leveraging the forward and reverse processes of the conditional diffusion model to add and remove noise progressively, we reconstruct original data from noisy inputs. Our extensive experiments demonstrate that diffusion model-based denoised time series significantly enhance the performance on downstream future return classification tasks. Moreover, trading signals derived from the denoised data yield more profitable trades with fewer transactions, thereby minimizing transaction costs and increasing overall trading efficiency. Finally, we show that by using classifiers trained on denoised time series, we can recognize the noising state of the market and obtain excess return. |
|
| Order-preserving pattern mining with forgetting mechanism | 2024-09-02 | ShowOrder-preserving pattern (OPP) mining is a type of sequential pattern mining method in which a group of ranks of time series is used to represent an OPP. This approach can discover frequent trends in time series. Existing OPP mining algorithms consider data points at different time to be equally important; however, newer data usually have a more significant impact, while older data have a weaker impact. We therefore introduce the forgetting mechanism into OPP mining to reduce the importance of older data. This paper explores the mining of OPPs with forgetting mechanism (OPF) and proposes an algorithm called OPF-Miner that can discover frequent OPFs. OPF-Miner performs two tasks, candidate pattern generation and support calculation. In candidate pattern generation, OPF-Miner employs a maximal support priority strategy and a group pattern fusion strategy to avoid redundant pattern fusions. For support calculation, we propose an algorithm called support calculation with forgetting mechanism, which uses prefix and suffix pattern pruning strategies to avoid redundant support calculations. The experiments are conducted on nine datasets and 12 alternative algorithms. The results verify that OPF-Miner is superior to other competitive algorithms. More importantly, OPF-Miner yields good clustering performance for time series, since the forgetting mechanism is employed. |
|
| Time series classification with random convolution kernels based transforms: pooling operators and input representations matter | 2024-09-02 | ShowThis article presents a new approach based on MiniRocket, called SelF-Rocket, for fast time series classification (TSC). Unlike existing approaches based on random convolution kernels, it dynamically selects the best couple of input representations and pooling operator during the training process. SelF-Rocket achieves state-of-the-art accuracy on the University of California Riverside (UCR) TSC benchmark datasets. |
|
| Benchmarking Time Series Databases with IoTDB-Benchmark for IoT Scenarios | 2024-09-02 | ShowWith the wide application of time series databases (TSDBs) in big data fields like cluster monitoring and industrial IoT, there have been developed a number of TSDBs for time series data management. Different TSDBs have test reports comparing themselves with other databases to show their advantages, but the comparisons are typically based on their own tools without using a common well-recognized test framework. To the best of our knowledge, there is no mature TSDB benchmark either. With the goal of establishing a standard of evaluating TSDB systems, we present the IoTDB-Benchmark framework, specifically designed for TSDB and IoT application scenarios. We pay close attention to some special data ingestion scenarios and summarize 10 basic queries types. We use this benchmark to compare four TSDB systems: InfluxDB, OpenTSDB, KairosDB and TimescaleDB. Our benchmark framework/tool not only measures performance metrics but also takes system resource consumption into consideration. |
|
| Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations | 2024-09-02 | ShowSea ice at the North Pole is vital to global climate dynamics. However, accurately forecasting sea ice poses a significant challenge due to the intricate interaction among multiple variables. Leveraging the capability to integrate multiple inputs and powerful performances seamlessly, many studies have turned to neural networks for sea ice forecasting. This paper introduces a novel deep architecture named Unicorn, designed to forecast weekly sea ice. Our model integrates multiple time series images within its architecture to enhance its forecasting performance. Moreover, we incorporate a bottleneck layer within the U-Net architecture, serving as neural ordinary differential equations with convolution operations, to capture the spatiotemporal dynamics of latent variables. Through real data analysis with datasets spanning from 1998 to 2021, our proposed model demonstrates significant improvements over state-of-the-art models in the sea ice concentration forecasting task. It achieves an average MAE improvement of 12% compared to benchmark models. Additionally, our method outperforms existing approaches in sea ice extent forecasting, achieving a classification performance improvement of approximately 18%. These experimental results show the superiority of our proposed model. |
|
| Sparse Discrete Empirical Interpolation Method: State Estimation from Few Sensors | 2024-09-01 | ShowDiscrete empirical interpolation method (DEIM) estimates a function from its incomplete pointwise measurements. Unfortunately, DEIM suffers large interpolation errors when few measurements are available. Here, we introduce Sparse DEIM (S-DEIM) for accurately estimating a function even when very few measurements are available. To this end, S-DEIM leverages a kernel vector which has been neglected in previous DEIM-based methods. We derive theoretical error estimates for S-DEIM, showing its relatively small error when an optimal kernel vector is used. When the function is generated by a continuous-time dynamical system, we propose a data assimilation algorithm which approximates the optimal kernel vector using observational time series. We prove that, under certain conditions, data assimilated S-DEIM converges exponentially fast towards the true state. We demonstrate the efficacy of our method on two numerical examples. |
Minor...Minor revisions. Accepted for publication in SIAM J. on Scientific Computing |
| Data-driven ODE modeling of the high-frequency complex dynamics of a fluid flow | 2024-09-01 | ShowIn our previous paper [N. Tsutsumi, K. Nakai and Y. Saiki, Chaos 32, 091101 (2022)], we proposed a method for constructing a system of differential equations of chaotic behavior from only observable deterministic time series, which we call the radial function-based regression (RfR) method. However, when the targeted variable's behavior is rather complex, the direct application of the RfR method does not function well. In this study, we propose a novel method of modeling such dynamics, including the high-frequency intermittent behavior of a fluid flow, by considering another variable (base variable) showing relatively simple, less intermittent behavior. We construct an autonomous joint model composed of two parts: the first is an autonomous system of a base variable, and the other concerns the targeted variable being affected by a term involving the base variable to demonstrate complex dynamics. The constructed joint model succeeded in not only inferring a short trajectory but also reconstructing chaotic sets and statistical properties obtained from a long trajectory such as the density distributions of the actual dynamics. |
7pages, 6figures |
| Title | Date | Abstract | Comment |
|---|---|---|---|
| Human Perception of LLM-generated Text Content in Social Media Environments | 2024-09-10 | ShowEmerging technologies, particularly artificial intelligence (AI), and more specifically Large Language Models (LLMs) have provided malicious actors with powerful tools for manipulating digital discourse. LLMs have the potential to affect traditional forms of democratic engagements, such as voter choice, government surveys, or even online communication with regulators; since bots are capable of producing large quantities of credible text. To investigate the human perception of LLM-generated content, we recruited over 1,000 participants who then tried to differentiate bot from human posts in social media discussion threads. We found that humans perform poorly at identifying the true nature of user posts on social media. We also found patterns in how humans identify LLM-generated text content in social media discourse. Finally, we observed the Uncanny Valley effect in text dialogue in both user perception and identification. This indicates that despite humans being poor at the identification process, they can still sense discomfort when reading LLM-generated content. |
|
| Strategic management analysis: from data to strategy diagram by LLM | 2024-09-10 | ShowStrategy management analyses are created by business consultants with common analysis frameworks (i.e. comparative analyses) and associated diagrams. We show these can be largely constructed using LLMs, starting with the extraction of insights from data, organization of those insights according to a strategy management framework, and then depiction in the typical strategy management diagram for that framework (static textual visualizations). We discuss caveats and future directions to generalize for broader uses. |
NLVIZ...NLVIZ Workshop at IEEE VIZ 2024. 7 pages, 5 figures |
| MAPS: Energy-Reliability Tradeoff Management in Autonomous Vehicles Through LLMs Penetrated Science | 2024-09-10 | ShowAs autonomous vehicles become more prevalent, highly accurate and efficient systems are increasingly critical to improve safety, performance, and energy consumption. Efficient management of energy-reliability tradeoffs in these systems demands the ability to predict various conditions during vehicle operations. With the promising improvement of Large Language Models (LLMs) and the emergence of well-known models like ChatGPT, unique opportunities for autonomous vehicle-related predictions have been provided in recent years. This paper proposed MAPS using LLMs as map reader co-drivers to predict the vital parameters to set during the autonomous vehicle operation to balance the energy-reliability tradeoff. The MAPS method demonstrates a 20% improvement in navigation accuracy compared to the best baseline method. MAPS also shows 11% energy savings in computational units and up to 54% in both mechanical and computational units. |
|
| Mapping News Narratives Using LLMs and Narrative-Structured Text Embeddings | 2024-09-10 | ShowGiven the profound impact of narratives across various societal levels, from personal identities to international politics, it is crucial to understand their distribution and development over time. This is particularly important in online spaces. On the Web, narratives can spread rapidly and intensify societal divides and conflicts. While many qualitative approaches exist, quantifying narratives remains a significant challenge. Computational narrative analysis lacks frameworks that are both comprehensive and generalizable. To address this gap, we introduce a numerical narrative representation grounded in structuralist linguistic theory. Chiefly, Greimas' Actantial Model represents a narrative through a constellation of six functional character roles. These so-called actants are genre-agnostic, making the model highly generalizable. We extract the actants using an open-source LLM and integrate them into a Narrative-Structured Text Embedding that captures both the semantics and narrative structure of a text. We demonstrate the analytical insights of the method on the example of 5000 full-text news articles from Al Jazeera and The Washington Post on the Israel-Palestine conflict. Our method successfully distinguishes articles that cover the same topics but differ in narrative structure. |
19 pa...19 pages, 13 figures, 4 tables |
| Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection | 2024-09-10 | ShowLarge vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) challenges by pairing images with textual descriptions indicative of normal and abnormal conditions, referred to as anomaly prompts. However, existing approaches depend on static anomaly prompts that are prone to cross-semantic ambiguity, and prioritize global image-level representations over crucial local pixel-level image-to-text alignment that is necessary for accurate anomaly localization. In this paper, we present ALFA, a training-free approach designed to address these challenges via a unified model. We propose a run-time prompt adaptation strategy, which first generates informative anomaly prompts to leverage the capabilities of a large language model (LLM). This strategy is enhanced by a contextual scoring mechanism for per-image anomaly prompt adaptation and cross-semantic ambiguity mitigation. We further introduce a novel fine-grained aligner to fuse local pixel-level semantics for precise anomaly localization, by projecting the image-text alignment from global to local semantic spaces. Extensive evaluations on MVTec and VisA datasets confirm ALFA's effectiveness in harnessing the language potential for zero-shot VAD, achieving significant PRO improvements of 12.1% on MVTec and 8.9% on VisA compared to state-of-the-art approaches. |
Accep...Accepted by MM'24 (Oral) |
| Leveraging LLMs, Graphs and Object Hierarchies for Task Planning in Large-Scale Environments | 2024-09-10 | ShowPlanning methods struggle with computational intractability in solving task-level problems in large-scale environments. This work explores leveraging the commonsense knowledge encoded in LLMs to empower planning techniques to deal with these complex scenarios. We achieve this by efficiently using LLMs to prune irrelevant components from the planning problem's state space, substantially simplifying its complexity. We demonstrate the efficacy of this system through extensive experiments within a household simulation environment, alongside real-world validation using a 7-DoF manipulator (video https://youtu.be/6ro2UOtOQS4). |
8 pages, 6 figures |
| Extracting Paragraphs from LLM Token Activations | 2024-09-10 | ShowGenerative large language models (LLMs) excel in natural language processing tasks, yet their inner workings remain underexplored beyond token-level predictions. This study investigates the degree to which these models decide the content of a paragraph at its onset, shedding light on their contextual understanding. By examining the information encoded in single-token activations, specifically the "\textbackslash n\textbackslash n" double newline token, we demonstrate that patching these activations can transfer significant information about the context of the following paragraph, providing further insights into the model's capacity to plan ahead. |
|
| LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA | 2024-09-10 | ShowThough current long-context large language models (LLMs) have demonstrated impressive capacities in answering user questions based on extensive text, the lack of citations in their responses makes user verification difficult, leading to concerns about their trustworthiness due to their potential hallucinations. In this work, we aim to enable long-context LLMs to generate responses with fine-grained sentence-level citations, improving their faithfulness and verifiability. We first introduce LongBench-Cite, an automated benchmark for assessing current LLMs' performance in Long-Context Question Answering with Citations (LQAC), revealing considerable room for improvement. To this end, we propose CoF (Coarse to Fine), a novel pipeline that utilizes off-the-shelf LLMs to automatically generate long-context QA instances with precise sentence-level citations, and leverage this pipeline to construct LongCite-45k, a large-scale SFT dataset for LQAC. Finally, we train LongCite-8B and LongCite-9B using the LongCite-45k dataset, successfully enabling their generation of accurate responses and fine-grained sentence-level citations in a single output. The evaluation results on LongBench-Cite show that our trained models achieve state-of-the-art citation quality, surpassing advanced proprietary models including GPT-4o. |
|
| Automate Strategy Finding with LLM in Quant investment | 2024-09-10 | ShowDespite significant progress in deep learning for financial trading, existing models often face instability and high uncertainty, hindering their practical application. Leveraging advancements in Large Language Models (LLMs) and multi-agent architectures, we propose a novel framework for quantitative stock investment in portfolio management and alpha mining. Our framework addresses these issues by integrating LLMs to generate diversified alphas and employing a multi-agent approach to dynamically evaluate market conditions. This paper proposes a framework where large language models (LLMs) mine alpha factors from multimodal financial data, ensuring a comprehensive understanding of market dynamics. The first module extracts predictive signals by integrating numerical data, research papers, and visual charts. The second module uses ensemble learning to construct a diverse pool of trading agents with varying risk preferences, enhancing strategy performance through a broader market analysis. In the third module, a dynamic weight-gating mechanism selects and assigns weights to the most relevant agents based on real-time market conditions, enabling the creation of an adaptive and context-aware composite alpha formula. Extensive experiments on the Chinese stock markets demonstrate that this framework significantly outperforms state-of-the-art baselines across multiple financial metrics. The results underscore the efficacy of combining LLM-generated alphas with a multi-agent architecture to achieve superior trading performance and stability. This work highlights the potential of AI-driven approaches in enhancing quantitative investment strategies and sets a new benchmark for integrating advanced machine learning techniques in financial trading can also be applied on diverse markets. |
|
| SHAPE-IT: Exploring Text-to-Shape-Display for Generative Shape-Changing Behaviors with LLMs | 2024-09-10 | ShowThis paper introduces text-to-shape-display, a novel approach to generating dynamic shape changes in pin-based shape displays through natural language commands. By leveraging large language models (LLMs) and AI-chaining, our approach allows users to author shape-changing behaviors on demand through text prompts without programming. We describe the foundational aspects necessary for such a system, including the identification of key generative elements (primitive, animation, and interaction) and design requirements to enhance user interaction, based on formative exploration and iterative design processes. Based on these insights, we develop SHAPE-IT, an LLM-based authoring tool for a 24 x 24 shape display, which translates the user's textual command into executable code and allows for quick exploration through a web-based control interface. We evaluate the effectiveness of SHAPE-IT in two ways: 1) performance evaluation and 2) user evaluation (N= 10). The study conclusions highlight the ability to facilitate rapid ideation of a wide range of shape-changing behaviors with AI. However, the findings also expose accuracy-related challenges and limitations, prompting further exploration into refining the framework for leveraging AI to better suit the unique requirements of shape-changing systems. |
Accep...Accepted for ACM UIST 2024 |
| NOVI : Chatbot System for University Novice with BERT and LLMs | 2024-09-10 | ShowTo mitigate the difficulties of university freshmen in adapting to university life, we developed NOVI, a chatbot system based on GPT-4o. This system utilizes post and comment data from SKKU 'Everytime', a university community site. Developed using LangChain, NOVI's performance has been evaluated with a BLEU score, Perplexity score, ROUGE-1 score, ROUGE-2 score, ROUGE-L score and METEOR score. This approach is not only limited to help university freshmen but is also expected to help various people adapting to new environments with different data. This research explores the development and potential application of new educational technology tools, contributing to easier social adaptation for beginners and settling a foundation for future advancement in LLM studies. |
|
| Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design | 2024-09-09 | ShowLarge Language Models (LLMs) are effective in computer hardware synthesis via hardware description language (HDL) generation. However, LLM-assisted approaches for HDL generation struggle when handling complex tasks. We introduce a suite of hierarchical prompting techniques which facilitate efficient stepwise design methods, and develop a generalizable automation pipeline for the process. To evaluate these techniques, we present a benchmark set of hardware designs which have solutions with or without architectural hierarchy. Using these benchmarks, we compare various open-source and proprietary LLMs, including our own fine-tuned Code Llama-Verilog model. Our hierarchical methods automatically produce successful designs for complex hardware modules that standard flat prompting methods cannot achieve, allowing smaller open-source LLMs to compete with large proprietary models. Hierarchical prompting reduces HDL generation time and yields savings on LLM costs. Our experiments detail which LLMs are capable of which applications, and how to apply hierarchical methods in various modes. We explore case studies of generating complex cores using automatic scripted hierarchical prompts, including the first-ever LLM-designed processor with no human feedback. Tools for the Recurrent Optimization via Machine Editing (ROME) method can be found at https://github.com/ajn313/ROME-LLM |
Accep...Accepted at MLCAD '24. 10 pages, 7 figures, 5 tables |
| User-LLM: Efficient LLM Contextualization with User Embeddings | 2024-09-09 | ShowLarge language models (LLMs) have achieved remarkable success across various domains, but effectively incorporating complex and potentially noisy user timeline data into LLMs remains a challenge. Current approaches often involve translating user timelines into text descriptions before feeding them to LLMs, which can be inefficient and may not fully capture the nuances of user behavior. Inspired by how LLMs are effectively integrated with images through direct embeddings, we propose User-LLM, a novel framework that leverages user embeddings to directly contextualize LLMs with user history interactions. These embeddings, generated by a user encoder pretrained using self-supervised learning on diverse user interactions, capture latent user behaviors and interests as well as their evolution over time. We integrate these user embeddings with LLMs through cross-attention, enabling LLMs to dynamically adapt their responses based on the context of a user's past actions and preferences. Our approach achieves significant efficiency gains by representing user timelines directly as embeddings, leading to substantial inference speedups of up to 78.1X. Comprehensive experiments on MovieLens, Amazon Review, and Google Local Review datasets demonstrate that User-LLM outperforms text-prompt-based contextualization on tasks requiring deep user understanding, with improvements of up to 16.33%, particularly excelling on long sequences that capture subtle shifts in user behavior. Furthermore, the incorporation of Perceiver layers streamlines the integration between user encoders and LLMs, yielding additional computational savings. |
|
| Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning | 2024-09-09 | ShowWe introduce Instruct-SkillMix, an automated approach for creating diverse, high quality SFT data. The Instruct-SkillMix pipeline involves two stages, each leveraging an existing powerful LLM: (1) Skill extraction: uses the LLM to extract core "skills" for instruction-following, either from existing datasets, or by directly prompting the model; (2) Data generation: uses the powerful LLM to generate (instruction, response) data that exhibit a randomly chosen pair of these skills. Here, the use of random skill combinations promotes diversity and difficulty. Vanilla SFT (i.e., no PPO, DPO, or RL methods) on data generated from Instruct-SkillMix leads to strong gains on instruction following benchmarks such as AlpacaEval 2.0, MT-Bench, and WildBench. With just $4$K examples, LLaMA-3-8B-Base achieves 42.76% length-controlled win rate on AlpacaEval 2.0. To our knowledge, this achieves state-of-the-art performance among all models that have only undergone SFT (no RL methods) and competes with proprietary models such as Claude 3 Opus and LLaMA-3.1-405B-Instruct. Ablation studies also suggest plausible reasons for why creating open instruction-tuning datasets via naive crowd-sourcing has proved difficult. Introducing low quality answers ("shirkers") in |
|
| LLMs Will Always Hallucinate, and We Need to Live With This | 2024-09-09 | ShowAs Large Language Models become more ubiquitous across domains, it becomes important to examine their inherent limitations critically. This work argues that hallucinations in language models are not just occasional errors but an inevitable feature of these systems. We demonstrate that hallucinations stem from the fundamental mathematical and logical structure of LLMs. It is, therefore, impossible to eliminate them through architectural improvements, dataset enhancements, or fact-checking mechanisms. Our analysis draws on computational theory and Godel's First Incompleteness Theorem, which references the undecidability of problems like the Halting, Emptiness, and Acceptance Problems. We demonstrate that every stage of the LLM process-from training data compilation to fact retrieval, intent classification, and text generation-will have a non-zero probability of producing hallucinations. This work introduces the concept of Structural Hallucination as an intrinsic nature of these systems. By establishing the mathematical certainty of hallucinations, we challenge the prevailing notion that they can be fully mitigated. |
|
| X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning | 2024-09-09 | ShowRecent research has achieved significant advancements in visual reasoning tasks through learning image-to-language projections and leveraging the impressive reasoning abilities of Large Language Models (LLMs). This paper introduces an efficient and effective framework that integrates multiple modalities (images, 3D, audio and video) to a frozen LLM and demonstrates an emergent ability for cross-modal reasoning (2+ modality inputs). Our approach explores two distinct projection mechanisms: Q-Formers and Linear Projections (LPs). Through extensive experimentation across all four modalities on 16 benchmarks, we explore both methods and assess their adaptability in integrated and separate cross-modal reasoning. The Q-Former projection demonstrates superior performance in single modality scenarios and adaptability in joint versus discriminative reasoning involving two or more modalities. However, it exhibits lower generalization capabilities than linear projection in contexts where task-modality data are limited. To enable this framework, we devise a scalable pipeline that automatically generates high-quality, instruction-tuning datasets from readily available captioning data across different modalities, and contribute 24K QA data for audio and 250K QA data for 3D. To facilitate further research in cross-modal reasoning, we introduce the DisCRn (Discriminative Cross-modal Reasoning) benchmark comprising 9K audio-video QA samples and 28K image-3D QA samples that require the model to reason discriminatively across disparate input modalities. |
|
| A System and Benchmark for LLM-based Q&A on Heterogeneous Data | 2024-09-09 | ShowIn many industrial settings, users wish to ask questions whose answers may be found in structured data sources such as a spreadsheets, databases, APIs, or combinations thereof. Often, the user doesn't know how to identify or access the right data source. This problem is compounded even further if multiple (and potentially siloed) data sources must be assembled to derive the answer. Recently, various Text-to-SQL applications that leverage Large Language Models (LLMs) have addressed some of these problems by enabling users to ask questions in natural language. However, these applications remain impractical in realistic industrial settings because they fail to cope with the data source heterogeneity that typifies such environments. In this paper, we address heterogeneity by introducing the siwarex platform, which enables seamless natural language access to both databases and APIs. To demonstrate the effectiveness of siwarex, we extend the popular Spider dataset and benchmark by replacing some of its tables by data retrieval APIs. We find that siwarex does a good job of coping with data source heterogeneity. Our modified Spider benchmark will soon be available to the research community |
|
| CauseJudger: Identifying the Cause with LLMs for Abductive Logical Reasoning | 2024-09-09 | ShowLarge language models (LLMs) have been utilized in solving diverse reasoning tasks, encompassing common sense, arithmetic and deduction tasks. However, with difficulties of reversing thinking patterns and irrelevant premises, how to determine the authenticity of the cause in abductive logical reasoning remains underexplored. Inspired by hypothesis and verification method and identification of irrelevant information in human thinking process, we propose a new framework for LLMs abductive logical reasoning called CauseJudger (CJ), which identifies the authenticity of possible cause by transforming thinking from reverse to forward and removing irrelevant information. In addition, we construct an abductive logical reasoning dataset for decision task called CauseLogics, which contains 200,000 tasks of varying reasoning lengths. Our experiments show the efficiency of CJ with overall experiments and ablation experiments as well as case studies on our dataset and reconstructed public dataset. Notably, CJ's implementation is efficient, requiring only two calls to LLM. Its impact is profound: when using gpt-3.5, CJ achieves a maximum correctness improvement of 41% compared to Zero-Shot-CoT. Moreover, with gpt-4, CJ attains an accuracy exceeding 90% across all datasets. |
|
| Online Advertisements with LLMs: Opportunities and Challenges | 2024-09-09 | ShowThis paper explores the potential for leveraging Large Language Models (LLM) in the realm of online advertising systems. We introduce a general framework for LLM advertisement, consisting of modification, bidding, prediction, and auction modules. Different design considerations for each module are presented. These design choices are evaluated and discussed based on essential desiderata required to maintain a sustainable system. Further fundamental questions regarding practicality, efficiency, and implementation challenges are raised for future research. Finally, we exposit how recent approaches on mechanism design for LLM can be framed in our unified perspective. |
|
| Jailbreaking Text-to-Image Models with LLM-Based Agents | 2024-09-09 | ShowRecent advancements have significantly improved automated task-solving capabilities using autonomous agents powered by large language models (LLMs). However, most LLM-based agents focus on dialogue, programming, or specialized domains, leaving their potential for addressing generative AI safety tasks largely unexplored. In this paper, we propose Atlas, an advanced LLM-based multi-agent framework targeting generative AI models, specifically focusing on jailbreak attacks against text-to-image (T2I) models with built-in safety filters. Atlas consists of two agents, namely the mutation agent and the selection agent, each comprising four key modules: a vision-language model (VLM) or LLM brain, planning, memory, and tool usage. The mutation agent uses its VLM brain to determine whether a prompt triggers the T2I model's safety filter. It then collaborates iteratively with the LLM brain of the selection agent to generate new candidate jailbreak prompts with the highest potential to bypass the filter. In addition to multi-agent communication, we leverage in-context learning (ICL) memory mechanisms and the chain-of-thought (COT) approach to learn from past successes and failures, thereby enhancing Atlas's performance. Our evaluation demonstrates that Atlas successfully jailbreaks several state-of-the-art T2I models equipped with multi-modal safety filters in a black-box setting. Additionally, Atlas outperforms existing methods in both query efficiency and the quality of generated images. This work convincingly demonstrates the successful application of LLM-based agents in studying the safety vulnerabilities of popular text-to-image generation models. We urge the community to consider advanced techniques like ours in response to the rapidly evolving text-to-image generation field. |
|
| AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents | 2024-09-09 | ShowAdvancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and updating their knowledge. Current LLM-based agents process past experiences using a full history of observations, summarization, retrieval augmentation. However, these unstructured memory representations do not facilitate the reasoning and planning essential for complex decision-making. In our study, we introduce AriGraph, a novel method wherein the agent constructs and updates a memory graph that integrates semantic and episodic memories while exploring the environment. We demonstrate that our Ariadne LLM agent, consisting of the proposed memory architecture augmented with planning and decision-making, effectively handles complex tasks within interactive text game environments difficult even for human players. Results show that our approach markedly outperforms other established memory methods and strong RL baselines in a range of problems of varying complexity. Additionally, AriGraph demonstrates competitive performance compared to dedicated knowledge graph-based methods in static multi-hop question-answering. |
Code ...Code for this work is avaliable at https://github.com/AIRI-Institute/AriGraph |
| Fine-Tuning, Quantization, and LLMs: Navigating Unintended Outcomes | 2024-09-09 | ShowLarge Language Models (LLMs) have gained widespread adoption across various domains, including chatbots and auto-task completion agents. However, these models are susceptible to safety vulnerabilities such as jailbreaking, prompt injection, and privacy leakage attacks. These vulnerabilities can lead to the generation of malicious content, unauthorized actions, or the disclosure of confidential information. While foundational LLMs undergo alignment training and incorporate safety measures, they are often subject to fine-tuning, or doing quantization resource-constrained environments. This study investigates the impact of these modifications on LLM safety, a critical consideration for building reliable and secure AI systems. We evaluate foundational models including Mistral, Llama series, Qwen, and MosaicML, along with their fine-tuned variants. Our comprehensive analysis reveals that fine-tuning generally increases the success rates of jailbreak attacks, while quantization has variable effects on attack success rates. Importantly, we find that properly implemented guardrails significantly enhance resistance to jailbreak attempts. These findings contribute to our understanding of LLM vulnerabilities and provide insights for developing more robust safety strategies in the deployment of language models. |
|
| ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities | 2024-09-09 | ShowIn this work, we introduce ChatQA 2, an Llama 3.0-based model with a 128K context window, designed to bridge the gap between open-source LLMs and leading proprietary models (e.g., GPT-4-Turbo) in long-context understanding and retrieval-augmented generation (RAG) capabilities. These two capabilities are essential for LLMs to process large volumes of information that cannot fit into a single prompt and are complementary to each other, depending on the downstream tasks and computational budgets. We present a detailed continued training recipe to extend the context window of Llama3-70B-base from 8K to 128K tokens, along with a three-stage instruction tuning process to enhance the model's instruction-following, RAG performance, and long-context understanding capabilities. Our results demonstrate that the Llama3-ChatQA-2-70B model outperforms most existing state-of-the-art models, including GPT-4-Turbo-2024-04-09, Qwen2-72B-Instruct, and Llama3.1-70B-Instruct, on ultra-long tasks beyond 100K tokens, as well as on the RAG benchmark using only a 4K context window, showing the strong long context capability across varying sequence lengths. We further provide extensive comparisons between direct long-context and RAG solutions using the same state-of-the-art long-context LLMs. Interestingly, we find that the performance of strong long-context LLMs using RAG improves when retrieving a larger number of chunks. With a large set of top-k chunks, RAG consistently outperforms direct long-context solution using the same state-of-the-art long-context models (e.g., Llama3-ChatQA-2-70B and Qwen2-72B-Instruct) on both 32K benchmarks and real-world 128K tasks. To advance research in this field, we open-sourced the model weights, training data, and the evaluation setup for the for the community: https://chatqa2-project.github.io/ |
v2: m...v2: major update with significantly improved results |
| $\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding | 2024-09-09 | ShowLarge language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this work, we propose a simple and effective \textbf{u}ncertainty-aware \textbf{s}elective \textbf{c}ontrastive \textbf{d}ecoding ( |
13pages,8 figures |
| A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems | 2024-09-09 | ShowThe integration of Large Language Models (LLMs) like GPT-4o into robotic systems represents a significant advancement in embodied artificial intelligence. These models can process multi-modal prompts, enabling them to generate more context-aware responses. However, this integration is not without challenges. One of the primary concerns is the potential security risks associated with using LLMs in robotic navigation tasks. These tasks require precise and reliable responses to ensure safe and effective operation. Multi-modal prompts, while enhancing the robot's understanding, also introduce complexities that can be exploited maliciously. For instance, adversarial inputs designed to mislead the model can lead to incorrect or dangerous navigational decisions. This study investigates the impact of prompt injections on mobile robot performance in LLM-integrated systems and explores secure prompt strategies to mitigate these risks. Our findings demonstrate a substantial overall improvement of approximately 30.8% in both attack detection and system performance with the implementation of robust defence mechanisms, highlighting their critical role in enhancing security and reliability in mission-oriented tasks. |
|
| Self-Reflection in LLM Agents: Effects on Problem-Solving Performance | 2024-09-08 | ShowIn this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline. For each incorrectly answered question, we instructed eight types of self-reflecting LLM agents to reflect on their mistakes and provide themselves with guidance to improve problem-solving. Then, using this guidance, each self-reflecting agent attempted to re-answer the same questions. Our results indicate that LLM agents are able to significantly improve their problem-solving performance through self-reflection ( |
|
| Using LLMs to Establish Implicit User Sentiment of Software Desirability | 2024-09-08 | ShowThis study explores the use of LLMs for providing quantitative zero-shot sentiment analysis of implicit software desirability, addressing a critical challenge in product evaluation where traditional review scores, though convenient, fail to capture the richness of qualitative user feedback. Innovations include establishing a method that 1) works with qualitative user experience data without the need for explicit review scores, 2) focuses on implicit user satisfaction, and 3) provides scaled numerical sentiment analysis, offering a more nuanced understanding of user sentiment, instead of simply classifying sentiment as positive, neutral, or negative. Data is collected using the Microsoft Product Desirability Toolkit (PDT), a well-known qualitative user experience analysis tool. For initial exploration, the PDT metric was given to users of two software systems. PDT data was fed through several LLMs (Claude Sonnet 3 and 3.5, GPT4, and GPT4o) and through a leading transfer learning technique, Twitter-Roberta-Base-Sentiment, and Vader, a leading sentiment analysis tool. Each system was asked to evaluate the data in two ways, by looking at the sentiment expressed in the PDT word/explanation pairs; and by looking at the sentiment expressed by the users in their grouped selection of five words and explanations, as a whole. Each LLM provided a sentiment score, its confidence (low, medium, high) in the score, and an explanation of the score. All LLMs tested were able to statistically detect user sentiment from the users' grouped data, whereas TRBS and Vader were not. The confidence and explanation of confidence provided by the LLMs assisted in understanding user sentiment. This study adds deeper understanding of evaluating user experiences, toward the goal of creating a universal tool that quantifies implicit sentiment. |
6 pag...6 pages, 2 figures, 2 tables, updated to incorporate feedback |
| OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs | 2024-09-08 | ShowDespite the recent advancements in Large Language Models (LLMs), which have significantly enhanced the generative capabilities for various NLP tasks, LLMs still face limitations in directly handling retrieval tasks. However, many practical applications demand the seamless integration of both retrieval and generation. This paper introduces a novel and efficient One-pass Generation and retrieval framework (OneGen), designed to improve LLMs' performance on tasks that require both generation and retrieval. The proposed framework bridges the traditionally separate training approaches for generation and retrieval by incorporating retrieval tokens generated autoregressively. This enables a single LLM to handle both tasks simultaneously in a unified forward pass. We conduct experiments on two distinct types of composite tasks, RAG and Entity Linking, to validate the pluggability, effectiveness, and efficiency of OneGen in training and inference. Furthermore, our results show that integrating generation and retrieval within the same context preserves the generative capabilities of LLMs while improving retrieval performance. To the best of our knowledge, OneGen is the first to enable LLMs to conduct vector retrieval during the generation. |
Work ...Work in progress; code is available at https://github.com/zjunlp/OneGen |
| Tasks People Prompt: A Taxonomy of LLM Downstream Tasks in Software Verification and Falsification Approaches | 2024-09-08 | ShowPrompting has become one of the main approaches to leverage emergent capabilities of Large Language Models [Brown et al. NeurIPS 2020, Wei et al. TMLR 2022, Wei et al. NeurIPS 2022]. Recently, researchers and practitioners have been "playing" with prompts (e.g., In-Context Learning) to see how to make the most of pre-trained Language Models. By homogeneously dissecting more than a hundred articles, we investigate how software testing and verification research communities have leveraged LLMs capabilities. First, we validate that downstream tasks are adequate to convey a nontrivial modular blueprint of prompt-based proposals in scope. Moreover, we name and classify the concrete downstream tasks we recover in both validation research papers and solution proposals. In order to perform classification, mapping, and analysis, we also develop a novel downstream-task taxonomy. The main taxonomy requirement is to highlight commonalities while exhibiting variation points of task types that enable pinpointing emerging patterns in a varied spectrum of Software Engineering problems that encompasses testing, fuzzing, fault localization, vulnerability detection, static analysis, and program verification approaches. Avenues for future research are also discussed based on conceptual clusters induced by the taxonomy. |
|
| LLM-based Abstraction and Concretization for GUI Test Migration | 2024-09-08 | ShowGUI test migration aims to produce test cases with events and assertions to test specific functionalities of a target app. Existing migration approaches typically focus on the widget-mapping paradigm that maps widgets from source apps to target apps. However, since different apps may implement the same functionality in different ways, direct mapping may result in incomplete or buggy test cases, thus significantly impacting the effectiveness of testing target functionality and the practical applicability. In this paper, we propose a new migration paradigm (i.e., abstraction-concretization paradigm) that first abstracts the test logic for the target functionality and then utilizes this logic to generate the concrete GUI test case. Furthermore, we introduce MACdroid, the first approach that migrates GUI test cases based on this paradigm. Specifically, we propose an abstraction technique that utilizes source test cases from source apps targeting the same functionality to extract a general test logic for that functionality. Then, we propose a concretization technique that utilizes the general test logic to guide an LLM in generating the corresponding GUI test case (including events and assertions) for the target app. We evaluate MACdroid on two widely-used datasets (including 31 apps, 34 functionalities, and 123 test cases). On the FrUITeR dataset, the test cases generated by MACdroid successfully test 64% of the target functionalities, improving the baselines by 191%. On the Lin dataset, MACdroid successfully tests 75% of the target functionalities, outperforming the baselines by 42%. These results underscore the effectiveness of MACdroid in GUI test migration. |
|
| Hint of Thought prompting: an explainable and zero-shot approach to reasoning tasks with LLMs | 2024-09-08 | ShowPrompting becomes an increasingly important research topic for better utilization of LLMs. Although simple prompting performs well on single-step questions, it cannot permanently activate the correct knowledge path for multi-step reasoning tasks. The chain of thought (CoT), which often contains zero-shot CoT and few-shot CoT, is a recently developed prompting method that can explain the reasoning process to the LLM and outperforms simple prompting in three challenging reasoning tasks, including arithmetic, symbolic, and commonsense reasoning. Inspired by zero-shot CoT, and further extending the zero-shot ability, this paper proposes a novel hint of thought (HoT) prompting with explain-ability and zero-shot generalization. It is decomposed into three steps: explainable sub-questions, logical reasoning, and answering. Such three steps are sequentially ordered in step-by-step hints, which can be easily adjusted and explained to different tasks. Finally, experimental results demonstrate that our HoT prompting has a significant advantage on the zero-shot reasoning task compared to existing zero-shot CoT. We did zero-shot experiments on math tasks like GSM8K, ADDSUB, AQUA, SVAMP, and commonsense tasks such as StrategyQA. In particular, the accuracy of the proposed HoT prompting is improved with GSM8K from 40.50% to 70.65%, with AQUA from 31.9% to 46.4%, with SVAMP from 63.7% to 76.9%, and with ADDSUB from 74.7% to 87.34%, respectively, which even defeats the competitive PoT approach on GSM8k, AQUA, and SVAMP. |
|
| InstInfer: In-Storage Attention Offloading for Cost-Effective Long-Context LLM Inference | 2024-09-08 | ShowThe widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache, which imposes a huge burden on the GPU VRAM, especially for resource-constraint scenarios (e.g., edge computing and personal devices). Several cost-effective solutions leverage host memory or SSDs to reduce storage costs for offline inference scenarios and improve the throughput. Nevertheless, they suffer from significant performance penalties imposed by intensive KV cache accesses due to limited PCIe bandwidth. To address these issues, we propose InstInfer, a novel LLM inference system that offloads the most performance-critical computation (i.e., attention in decoding phase) and data (i.e., KV cache) parts to Computational Storage Drives (CSDs), which minimize the enormous KV transfer overheads. InstInfer designs a dedicated flash-aware in-storage attention engine with KV cache management mechanisms to exploit the high internal bandwidths of CSDs instead of being limited by the PCIe bandwidth. The optimized P2P transmission between GPU and CSDs further reduces data migration overheads. Experimental results demonstrate that for a 13B model using an NVIDIA A6000 GPU, InstInfer improves throughput for long-sequence inference by up to 11.1$\times$, compared to existing SSD-based solutions such as FlexGen. |
|
| How to Align Large Language Models for Teaching English? Designing and Developing LLM based-Chatbot for Teaching English Conversation in EFL, Findings and Limitations | 2024-09-08 | ShowThis study investigates the design, development, and evaluation of a Large Language Model (LLM)-based chatbot for teaching English conversations in an English as a Foreign Language (EFL) context. Employing the Design and Development Research (DDR), we analyzed needs, established design principles, and iteratively refined a chatbot through experimenting various LLMs and alignment methods. Through both quantitative and qualitative evaluations, we identified the most effective LLM and its prompt combination to generate high-quality, contextually appropriate responses. Interviews with teachers provided insights into desirable system features, potential educational applications, and ethical considerations in the development and deployment of the chatbots. The design iterations yielded the importance of feedback mechanisms and customizable AI personas. Future research should explore adaptive feedback strategies, collaborative approaches with various stakeholders, and the integration of insights from human-computer interaction (HCI) and user experience (UX) design. This study contributes to the growing body of research on applying LLMs in language education, providing insights and recommendations for the design, development, and evaluation of LLM-based chatbots for EFL conversation practice. As the field evolves, ongoing research and collaboration among educators, AI engineers, and other stakeholders will be essential to harness the potential of these technologies to enhance language learning experiences. |
56 pages |
| Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue | 2024-09-07 | ShowIn recent years, we have observed a rapid advancement in speech language models (SpeechLLMs), catching up with humans' listening and reasoning abilities. Remarkably, SpeechLLMs have demonstrated impressive spoken dialogue question-answering (SQA) performance in benchmarks like Gaokao, the English listening test of the college entrance exam in China, which seemingly requires understanding both the spoken content and voice characteristics of speakers in a conversation. However, after carefully examining Gaokao's questions, we find the correct answers to many questions can be inferred from the conversation context alone without identifying the speaker asked in the question. Our evaluation of state-of-the-art models Qwen-Audio and WavLLM in both Gaokao and our proposed "What Do You Like?" dataset shows a significantly higher accuracy in these context-based questions than in identity-critical questions, which can only be answered correctly with correct speaker identification. Our results and analysis suggest that when solving SQA, the current SpeechLLMs exhibit limited speaker awareness from the audio and behave similarly to an LLM reasoning from the conversation transcription without sound. We propose that our definitions and automated classification of context-based and identity-critical questions could offer a more accurate evaluation framework of SpeechLLMs in SQA tasks. |
Accep...Accepted to IEEE SLT 2024 |
| The Fellowship of the LLMs: Multi-Agent Workflows for Synthetic Preference Optimization Dataset Generation | 2024-09-07 | ShowThis paper presents synthetic Preference Optimization (PO) datasets generated using multi-agent workflows and evaluates the effectiveness and potential of these workflows in the dataset generation process. PO dataset generation requires two modules: (1) response evaluation, and (2) response generation. In the response evaluation module, the responses from Large Language Models (LLMs) are evaluated and ranked - a task typically carried out by human annotators that we automate using LLMs. We assess the response evaluation module in a 2 step process. In step 1, we assess LLMs as evaluators using three distinct prompting strategies. In step 2, we apply the winning prompting strategy to compare the performance of LLM-as-a-Judge, LLMs-as-a-Jury, and LLM Debate. In each step, we use inter-rater agreement using Cohen's Kappa between human annotators and LLMs. For the response generation module, we compare different configurations for the LLM Feedback Loop using the identified LLM evaluator configuration. We use the win rate (the fraction of times a generation framework is selected as the best by an LLM evaluator) to determine the best multi-agent configuration for generation. After identifying the best configurations for both modules, we use models from the GPT, Gemma, and Llama families to generate our PO datasets using the above pipeline. We generate two types of PO datasets, one to improve the generation capabilities of individual LLM and the other to improve the multi-agent workflow. Our evaluation shows that GPT-4o-as-a-Judge is more consistent across datasets when the candidate responses do not include responses from the GPT family. Additionally, we find that the LLM Feedback Loop, with Llama as the generator and Gemma as the reviewer, achieves a notable 71.8% and 73.8% win rate over single-agent Llama and Gemma, respectively. |
|
| Incorporate LLMs with Influential Recommender System | 2024-09-07 | ShowRecommender systems have achieved increasing accuracy over the years. However, this precision often leads users to narrow their interests, resulting in issues such as limited diversity and the creation of echo chambers. Current research addresses these challenges through proactive recommender systems by recommending a sequence of items (called influence path) to guide user interest in the target item. However, existing methods struggle to construct a coherent influence path that builds up with items the user is likely to enjoy. In this paper, we leverage the Large Language Model's (LLMs) exceptional ability for path planning and instruction following, introducing a novel approach named LLM-based Influence Path Planning (LLM-IPP). Our approach maintains coherence between consecutive recommendations and enhances user acceptability of the recommended items. To evaluate LLM-IPP, we implement various user simulators and metrics to measure user acceptability and path coherence. Experimental results demonstrate that LLM-IPP significantly outperforms traditional proactive recommender systems. This study pioneers the integration of LLMs into proactive recommender systems, offering a reliable and user-engaging methodology for future recommendation technologies. |
5 pages, 1 figure |
| HULLMI: Human vs LLM identification with explainability | 2024-09-07 | ShowAs LLMs become increasingly proficient at producing human-like responses, there has been a rise of academic and industrial pursuits dedicated to flagging a given piece of text as "human" or "AI". Most of these pursuits involve modern NLP detectors like T5-Sentinel and RoBERTa-Sentinel, without paying too much attention to issues of interpretability and explainability of these models. In our study, we provide a comprehensive analysis that shows that traditional ML models (Naive-Bayes,MLP, Random Forests, XGBoost) perform as well as modern NLP detectors, in human vs AI text detection. We achieve this by implementing a robust testing procedure on diverse datasets, including curated corpora and real-world samples. Subsequently, by employing the explainable AI technique LIME, we uncover parts of the input that contribute most to the prediction of each model, providing insights into the detection process. Our study contributes to the growing need for developing production-level LLM detection tools, which can leverage a wide range of traditional as well as modern NLP detectors we propose. Finally, the LIME techniques we demonstrate also have the potential to equip these detection tools with interpretability analysis features, making them more reliable and trustworthy in various domains like education, healthcare, and media. |
17 pages, 8 figures |
| HowToCaption: Prompting LLMs to Transform Video Annotations at Scale | 2024-09-07 | ShowInstructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast to human-annotated captions, both speech and subtitles naturally differ from the visual content of the videos and thus provide only noisy supervision. As a result, large-scale annotation-free web video training data remains sub-optimal for training text-video models. In this work, we propose to leverage the capabilities of large language models (LLMs) to obtain high-quality video descriptions aligned with videos at scale. Specifically, we prompt an LLM to create plausible video captions based on ASR subtitles of instructional videos. To this end, we introduce a prompting method that is able to take into account a longer text of subtitles, allowing us to capture the contextual information beyond one single sentence. We further prompt the LLM to generate timestamps for each produced caption based on the timestamps of the subtitles and finally align the generated captions to the video temporally. In this way, we obtain human-style video captions at scale without human supervision. We apply our method to the subtitles of the HowTo100M dataset, creating a new large-scale dataset, HowToCaption. Our evaluation shows that the resulting captions not only significantly improve the performance over many different benchmark datasets for zero-shot text-video retrieval and video captioning, but also lead to a disentangling of textual narration from the audio, boosting the performance in text-video-audio tasks. |
|
| Cross-Data Knowledge Graph Construction for LLM-enabled Educational Question-Answering System: A Case Study at HCMUT | 2024-09-07 | ShowIn today's rapidly evolving landscape of Artificial Intelligence, large language models (LLMs) have emerged as a vibrant research topic. LLMs find applications in various fields and contribute significantly. Despite their powerful language capabilities, similar to pre-trained language models (PLMs), LLMs still face challenges in remembering events, incorporating new information, and addressing domain-specific issues or hallucinations. To overcome these limitations, researchers have proposed Retrieval-Augmented Generation (RAG) techniques, some others have proposed the integration of LLMs with Knowledge Graphs (KGs) to provide factual context, thereby improving performance and delivering more accurate feedback to user queries. Education plays a crucial role in human development and progress. With the technology transformation, traditional education is being replaced by digital or blended education. Therefore, educational data in the digital environment is increasing day by day. Data in higher education institutions are diverse, comprising various sources such as unstructured/structured text, relational databases, web/app-based API access, etc. Constructing a Knowledge Graph from these cross-data sources is not a simple task. This article proposes a method for automatically constructing a Knowledge Graph from multiple data sources and discusses some initial applications (experimental trials) of KG in conjunction with LLMs for question-answering tasks. |
8 pag...8 pages, 7 figures, Accepted at AIQAM '24: Proceedings of the 1st ACM Workshop on AI-Powered Q&A Systems for Multimedia |
| DeliGrasp: Inferring Object Properties with LLMs for Adaptive Grasp Policies | 2024-09-06 | ShowLarge language models (LLMs) can provide rich physical descriptions of most worldly objects, allowing robots to achieve more informed and capable grasping. We leverage LLMs' common sense physical reasoning and code-writing abilities to infer an object's physical characteristics$\unicode{x2013}$mass |
|
| The emergence of Large Language Models (LLM) as a tool in literature reviews: an LLM automated systematic review | 2024-09-06 | ShowObjective: This study aims to summarize the usage of Large Language Models (LLMs) in the process of creating a scientific review. We look at the range of stages in a review that can be automated and assess the current state-of-the-art research projects in the field. Materials and Methods: The search was conducted in June 2024 in PubMed, Scopus, Dimensions, and Google Scholar databases by human reviewers. Screening and extraction process took place in Covidence with the help of LLM add-on which uses OpenAI gpt-4o model. ChatGPT was used to clean extracted data and generate code for figures in this manuscript, ChatGPT and Scite.ai were used in drafting all components of the manuscript, except the methods and discussion sections. Results: 3,788 articles were retrieved, and 172 studies were deemed eligible for the final review. ChatGPT and GPT-based LLM emerged as the most dominant architecture for review automation (n=126, 73.2%). A significant number of review automation projects were found, but only a limited number of papers (n=26, 15.1%) were actual reviews that used LLM during their creation. Most citations focused on automation of a particular stage of review, such as Searching for publications (n=60, 34.9%), and Data extraction (n=54, 31.4%). When comparing pooled performance of GPT-based and BERT-based models, the former were better in data extraction with mean precision 83.0% (SD=10.4), and recall 86.0% (SD=9.8), while being slightly less accurate in title and abstract screening stage (Maccuracy=77.3%, SD=13.0). Discussion/Conclusion: Our LLM-assisted systematic review revealed a significant number of research projects related to review automation using LLMs. The results looked promising, and we anticipate that LLMs will change in the near future the way the scientific reviews are conducted. |
18 ma...18 main pages with 5 figures and 1 table, references, followed by supplementary materials |
| Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance | 2024-09-06 | ShowAs scientific research proliferates, researchers face the daunting task of navigating and reading vast amounts of literature. Existing solutions, such as document QA, fail to provide personalized and up-to-date information efficiently. We present Paper Copilot, a self-evolving, efficient LLM system designed to assist researchers, based on thought-retrieval, user profile and high performance optimization. Specifically, Paper Copilot can offer personalized research services, maintaining a real-time updated database. Quantitative evaluation demonstrates that Paper Copilot saves 69.92% of time after efficient deployment. This paper details the design and implementation of Paper Copilot, highlighting its contributions to personalized academic support and its potential to streamline the research process. |
|
| RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs | 2024-09-06 | ShowLLM-powered personalization agent systems employ Large Language Models (LLMs) to predict users' behavior from their past activities. However, their effectiveness often hinges on the ability to effectively leverage extensive, long user historical data due to its inherent noise and length of such data. Existing pretrained LLMs may generate summaries that are concise but lack the necessary context for downstream tasks, hindering their utility in personalization systems. To address these challenges, we introduce Reinforcement Learning from Prediction Feedback (RLPF). RLPF fine-tunes LLMs to generate concise, human-readable user summaries that are optimized for downstream task performance. By maximizing the usefulness of the generated summaries, RLPF effectively distills extensive user history data while preserving essential information for downstream tasks. Our empirical evaluation demonstrates significant improvements in both extrinsic downstream task utility and intrinsic summary quality, surpassing baseline methods by up to 22% on downstream task performance and achieving an up to 84.59% win rate on Factuality, Abstractiveness, and Readability. RLPF also achieves a remarkable 74% reduction in context length while improving performance on 16 out of 19 unseen tasks and/or datasets, showcasing its generalizability. This approach offers a promising solution for enhancing LLM personalization by effectively transforming long, noisy user histories into informative and human-readable representations. |
|
| Toward LLM-Powered Social Robots for Supporting Sensitive Disclosures of Stigmatized Health Conditions | 2024-09-06 | ShowDisclosing sensitive health conditions offers significant benefits at both individual and societal levels. However, patients often face challenges due to concerns about stigma. The use of social robots and chatbots to support sensitive disclosures is gaining traction, especially with the emergence of LLM models. Yet, numerous technical, ethical, privacy, safety, efficacy, and reporting concerns must be carefully addressed in this context. In this position paper, we focus on the example of HIV status disclosure, examining key opportunities, technical considerations, and risks associated with LLM-backed social robotics. |
|
| Are LLM-based methods good enough for detecting unfair terms of service? | 2024-09-06 | ShowCountless terms of service (ToS) are being signed everyday by users all over the world while interacting with all kinds of apps and websites. More often than not, these online contracts spanning double-digit pages are signed blindly by users who simply want immediate access to the desired service. What would normally require a consultation with a legal team, has now become a mundane activity consisting of a few clicks where users potentially sign away their rights, for instance in terms of their data privacy, to countless online entities/companies. Large language models (LLMs) are good at parsing long text-based documents, and could potentially be adopted to help users when dealing with dubious clauses in ToS and their underlying privacy policies. To investigate the utility of existing models for this task, we first build a dataset consisting of 12 questions applied individually to a set of privacy policies crawled from popular websites. Thereafter, a series of open-source as well as commercial chatbots such as ChatGPT, are queried over each question, with the answers being compared to a given ground truth. Our results show that some open-source models are able to provide a higher accuracy compared to some commercial models. However, the best performance is recorded from a commercial chatbot (ChatGPT4). Overall, all models perform only slightly better than random at this task. Consequently, their performance needs to be significantly improved before they can be adopted at large for this purpose. |
|
| AGR: Age Group fairness Reward for Bias Mitigation in LLMs | 2024-09-06 | ShowLLMs can exhibit age biases, resulting in unequal treatment of individuals across age groups. While much research has addressed racial and gender biases, age bias remains little explored. The scarcity of instruction-tuning and preference datasets for age bias hampers its detection and measurement, and existing fine-tuning methods seldom address age-related fairness. In this paper, we construct age bias preference datasets and instruction-tuning datasets for RLHF. We introduce ARG, an age fairness reward to reduce differences in the response quality of LLMs across different age groups. Extensive experiments demonstrate that this reward significantly improves response accuracy and reduces performance disparities across age groups. Our source code and datasets are available at the anonymous \href{https://anonymous.4open.science/r/FairRLHF-D445/readme.md}{link}. |
The f...The first two authors contributed equally to this work. Corresponding to Zhiqiang Wang. ACKNOWLEDGMENT: we would like to thank the computing resources support from the State Key Laboratory of New Computer Software Technologies at Nanjing University |
| Zero-Shot Topic Classification of Column Headers: Leveraging LLMs for Metadata Enrichment | 2024-09-06 | ShowTraditional dataset retrieval systems rely on metadata for indexing, rather than on the underlying data values. However, high-quality metadata creation and enrichment often require manual annotations, which is a labour-intensive and challenging process to automate. In this study, we propose a method to support metadata enrichment using topic annotations generated by three Large Language Models (LLMs): ChatGPT-3.5, GoogleBard, and GoogleGemini. Our analysis focuses on classifying column headers based on domain-specific topics from the Consortium of European Social Science Data Archives (CESSDA), a Linked Data controlled vocabulary. Our approach operates in a zero-shot setting, integrating the controlled topic vocabulary directly within the input prompt. This integration serves as a Large Context Windows approach, with the aim of improving the results of the topic classification task. We evaluated the performance of the LLMs in terms of internal consistency, inter-machine alignment, and agreement with human classification. Additionally, we investigate the impact of contextual information (i.e., dataset description) on the classification outcomes. Our findings suggest that ChatGPT and GoogleGemini outperform GoogleBard in terms of internal consistency as well as LLM-human-agreement. Interestingly, we found that contextual information had no significant impact on LLM performance. This work proposes a novel approach that leverages LLMs for topic classification of column headers using a controlled vocabulary, presenting a practical application of LLMs and Large Context Windows within the Semantic Web domain. This approach has the potential to facilitate automated metadata enrichment, thereby enhancing dataset retrieval and the Findability, Accessibility, Interoperability, and Reusability (FAIR) of research data on the Web. |
|
| Learning vs Retrieval: The Role of In-Context Examples in Regression with LLMs | 2024-09-06 | ShowGenerative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit ICL are not always consistent. In this work, we propose a framework for evaluating in-context learning mechanisms, which we claim are a combination of retrieving internal knowledge and learning from in-context examples by focusing on regression tasks. First, we show that LLMs can perform regression on real-world datasets and then design experiments to measure the extent to which the LLM retrieves its internal knowledge versus learning from in-context examples. We argue that this process lies on a spectrum between these two extremes. We provide an in-depth analysis of the degrees to which these mechanisms are triggered depending on various factors, such as prior knowledge about the tasks and the type and richness of the information provided by the in-context examples. We employ three LLMs and utilize multiple datasets to corroborate the robustness of our findings. Our results shed light on how to engineer prompts to leverage meta-learning from in-context examples and foster knowledge retrieval depending on the problem being addressed. |
|
| Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Question Answering | 2024-09-06 | ShowAdvancements in natural language processing have revolutionized the way we can interact with digital information systems, such as databases, making them more accessible. However, challenges persist, especially when accuracy is critical, as in the biomedical domain. A key issue is the hallucination problem, where models generate information unsupported by the underlying data, potentially leading to dangerous misinformation. This paper presents a novel approach designed to bridge this gap by combining Large Language Models (LLM) and Knowledge Graphs (KG) to improve the accuracy and reliability of question-answering systems, on the example of a biomedical KG. Built on the LangChain framework, our method incorporates a query checker that ensures the syntactical and semantic validity of LLM-generated queries, which are then used to extract information from a Knowledge Graph, substantially reducing errors like hallucinations. We evaluated the overall performance using a new benchmark dataset of 50 biomedical questions, testing several LLMs, including GPT-4 Turbo and llama3:70b. Our results indicate that while GPT-4 Turbo outperforms other models in generating accurate queries, open-source models like llama3:70b show promise with appropriate prompt engineering. To make this approach accessible, a user-friendly web-based interface has been developed, allowing users to input natural language queries, view generated and corrected Cypher queries, and verify the resulting paths for accuracy. Overall, this hybrid approach effectively addresses common issues such as data gaps and hallucinations, offering a reliable and intuitive solution for question answering systems. The source code for generating the results of this paper and for the user-interface can be found in our Git repository: https://git.zib.de/lpusch/cyphergenkg-gui |
|
| From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks | 2024-09-06 | ShowTo reduce the need for human annotations, large language models (LLMs) have been proposed as judges of the quality of other candidate models. LLM judges are typically evaluated by measuring the correlation with human judgments on generation tasks such as summarization or machine translation. In contrast, we study LLM judges on mathematical reasoning tasks. These tasks require multi-step reasoning, and the correctness of their solutions is verifiable, enabling a more objective evaluation. We perform a detailed performance analysis and find that the used judges are mostly unable to improve task performance but are able to pick the better model. Our analysis uncovers a strong correlation between judgment performance and the candidate model task performance. We observe that judges tend to choose the model of higher quality even if its answer is incorrect. Further, we show that it is possible to use statistics, such as the task performances of the individual models, to predict judgment performance. In an ablation, we either swap or mask the candidate answers and observe that judges often keep the original judgment, providing evidence that judges incorporate writing style in their judgments. In summary, we find that regularities in the judgments are quantifiable using statistical measures and provide various angles on exploiting them. |
|
| QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering | 2024-09-06 | ShowThe matrix quantization entails representing matrix elements in a more space-efficient form to reduce storage usage, with dequantization restoring the original matrix for use. We formulate the Quantization Error Minimization (QEM) problem as minimizing the distance between a matrix before and after quantization, under the condition that the quantized matrix occupies the same memory space. Matrix quantization is crucial in various applications, including Large Language Models (LLMs) weight quantization, vector databases, KV cache quantization, graph compression, and image compression. Recent advancements in LLMs, such as GPT-4 and BERT, have highlighted the importance of matrix compression due to the large size of parameters and KV cache, which are stored as matrices. We propose Quantum Entanglement Trees (QET) to address the QEM problem by leveraging the local orderliness of matrix elements, involving iterative element swapping to form a locally ordered matrix. This matrix is then grouped and quantized by columns. To enhance QET, we introduce two optimizations: further quantizing residuals to reduce MSE, and using masking and batch processing to accelerate the algorithm. Experimental results demonstrate that QET can effectively reduce MSE to 5.05%, 13.33%, and 11.89% of the current best method on the LLM dataset, K cache, and V cache, respectively. Our contributions include the abstraction of the QEM problem, the design of the QET algorithm, and the proposal of two optimizations to improve accuracy and speed. |
|
| Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers | 2024-09-06 | ShowRecent advancements in large language models (LLMs) have sparked optimism about their potential to accelerate scientific discovery, with a growing number of works proposing research agents that autonomously generate and validate new ideas. Despite this, no evaluations have shown that LLM systems can take the very first step of producing novel, expert-level ideas, let alone perform the entire research process. We address this by establishing an experimental design that evaluates research idea generation while controlling for confounders and performs the first head-to-head comparison between expert NLP researchers and an LLM ideation agent. By recruiting over 100 NLP researchers to write novel ideas and blind reviews of both LLM and human ideas, we obtain the first statistically significant conclusion on current LLM capabilities for research ideation: we find LLM-generated ideas are judged as more novel (p < 0.05) than human expert ideas while being judged slightly weaker on feasibility. Studying our agent baselines closely, we identify open problems in building and evaluating research agents, including failures of LLM self-evaluation and their lack of diversity in generation. Finally, we acknowledge that human judgements of novelty can be difficult, even by experts, and propose an end-to-end study design which recruits researchers to execute these ideas into full projects, enabling us to study whether these novelty and feasibility judgements result in meaningful differences in research outcome. |
main ...main paper is 20 pages |
| LLM-based multi-agent poetry generation in non-cooperative environments | 2024-09-06 | ShowDespite substantial progress of large language models (LLMs) for automatic poetry generation, the generated poetry lacks diversity while the training process differs greatly from human learning. Under the rationale that the learning process of the poetry generation systems should be more human-like and their output more diverse and novel, we introduce a framework based on social learning where we emphasize non-cooperative interactions besides cooperative interactions to encourage diversity. Our experiments are the first attempt at LLM-based multi-agent systems in non-cooperative environments for poetry generation employing both TRAINING-BASED agents (GPT-2) and PROMPTING-BASED agents (GPT-3 and GPT-4). Our evaluation based on 96k generated poems shows that our framework benefits the poetry generation process for TRAINING-BASED agents resulting in 1) a 3.0-3.7 percentage point (pp) increase in diversity and a 5.6-11.3 pp increase in novelty according to distinct and novel n-grams. The generated poetry from TRAINING-BASED agents also exhibits group divergence in terms of lexicons, styles and semantics. PROMPTING-BASED agents in our framework also benefit from non-cooperative environments and a more diverse ensemble of models with non-homogeneous agents has the potential to further enhance diversity, with an increase of 7.0-17.5 pp according to our experiments. However, PROMPTING-BASED agents show a decrease in lexical diversity over time and do not exhibit the group-based divergence intended in the social network. Our paper argues for a paradigm shift in creative tasks such as automatic poetry generation to include social learning processes (via LLM-based agent modeling) similar to human interaction. |
preprint |
| A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage | 2024-09-06 | ShowRunning LLMs on end devices has garnered significant attention recently due to their advantages in privacy preservation. With the advent of lightweight LLM models and specially designed GPUs, on-device LLM inference has achieved the necessary accuracy and performance metrics. However, we have identified that LLM inference on GPUs can leak privacy-sensitive intermediate information, specifically the KV pairs. An attacker could exploit these KV pairs to reconstruct the entire user conversation, leading to significant vulnerabilities. Existing solutions, such as Fully Homomorphic Encryption (FHE) and Trusted Execution Environments (TEE), are either too computation-intensive or resource-limited. To address these issues, we designed KV-Shield, which operates in two phases. In the initialization phase, it permutes the weight matrices so that all KV pairs are correspondingly permuted. During the runtime phase, the attention vector is inversely permuted to ensure the correctness of the layer output. All permutation-related operations are executed within the TEE, ensuring that insecure GPUs cannot access the original KV pairs, thus preventing conversation reconstruction. Finally, we theoretically analyze the correctness of KV-Shield, along with its advantages and overhead. |
|
| MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues | 2024-09-06 | ShowAutomatic Speech Recognition (ASR) systems are pivotal in transcribing speech into text, yet the errors they introduce can significantly degrade the performance of downstream tasks like summarization. This issue is particularly pronounced in clinical dialogue summarization, a low-resource domain where supervised data for fine-tuning is scarce, necessitating the use of ASR models as black-box solutions. Employing conventional data augmentation for enhancing the noise robustness of summarization models is not feasible either due to the unavailability of sufficient medical dialogue audio recordings and corresponding ASR transcripts. To address this challenge, we propose MEDSAGE, an approach for generating synthetic samples for data augmentation using Large Language Models (LLMs). Specifically, we leverage the in-context learning capabilities of LLMs and instruct them to generate ASR-like errors based on a few available medical dialogue examples with audio recordings. Experimental results show that LLMs can effectively model ASR noise, and incorporating this noisy data into the training process significantly improves the robustness and accuracy of medical dialogue summarization systems. This approach addresses the challenges of noisy ASR outputs in critical applications, offering a robust solution to enhance the reliability of clinical dialogue summarization. |
|
| Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction | 2024-09-06 | ShowRecent developments in pretrained large language models (LLMs) applied to robotics have demonstrated their capacity for sequencing a set of discrete skills to achieve open-ended goals in simple robotic tasks. In this paper, we examine the topic of LLM planning for a set of continuously parameterized skills whose execution must avoid violations of a set of kinematic, geometric, and physical constraints. We prompt the LLM to output code for a function with open parameters, which, together with environmental constraints, can be viewed as a Continuous Constraint Satisfaction Problem (CCSP). This CCSP can be solved through sampling or optimization to find a skill sequence and continuous parameter settings that achieve the goal while avoiding constraint violations. Additionally, we consider cases where the LLM proposes unsatisfiable CCSPs, such as those that are kinematically infeasible, dynamically unstable, or lead to collisions, and re-prompt the LLM to form a new CCSP accordingly. Experiments across three different simulated 3D domains demonstrate that our proposed strategy, PRoC3S, is capable of solving a wide range of complex manipulation tasks with realistic constraints on continuous parameters much more efficiently and effectively than existing baselines. |
|
| SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses | 2024-09-06 | ShowCan LLMs consistently improve their previous outputs for better results? For this to be true, LLMs would need to be better at discriminating among previously-generated alternatives, than generating initial responses. We explore the validity of this hypothesis in practice. We first formulate a unified framework that allows us to compare the generative and discriminative capability of any model on any task. In our resulting experimental analysis of several open-source and industrial LLMs, we observe that models are not reliably better at discriminating among previously-generated alternatives than generating initial responses. This finding challenges the notion that LLMs may be able to enhance their performance only through their own judgment. |
|
| On The Role of Prompt Construction In Enhancing Efficacy and Efficiency of LLM-Based Tabular Data Generation | 2024-09-06 | ShowLLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that enriching prompts with domain-specific insights can improve both the quality and efficiency of data generation. To test this hypothesis, we explore three prompt construction protocols: Expert-guided, LLM-guided, and Novel-Mapping. Through empirical studies with the recently proposed GReaT framework, we find that context-enriched prompts lead to significantly improved data generation quality and training efficiency. |
|
| Harnessing LLMs for Cross-City OD Flow Prediction | 2024-09-05 | ShowUnderstanding and predicting Origin-Destination (OD) flows is crucial for urban planning and transportation management. Traditional OD prediction models, while effective within single cities, often face limitations when applied across different cities due to varied traffic conditions, urban layouts, and socio-economic factors. In this paper, by employing Large Language Models (LLMs), we introduce a new method for cross-city OD flow prediction. Our approach leverages the advanced semantic understanding and contextual learning capabilities of LLMs to bridge the gap between cities with different characteristics, providing a robust and adaptable solution for accurate OD flow prediction that can be transferred from one city to another. Our novel framework involves four major components: collecting OD training datasets from a source city, instruction-tuning the LLMs, predicting destination POIs in a target city, and identifying the locations that best match the predicted destination POIs. We introduce a new loss function that integrates POI semantics and trip distance during training. By extracting high-quality semantic features from human mobility and POI data, the model understands spatial and functional relationships within urban spaces and captures interactions between individuals and various POIs. Extensive experimental results demonstrate the superiority of our approach over the state-of-the-art learning-based methods in cross-city OD flow prediction. |
12 pages, 18 figures |
| RETAIN: Interactive Tool for Regression Testing Guided LLM Migration | 2024-09-05 | ShowLarge Language Models (LLMs) are increasingly integrated into diverse applications. The rapid evolution of LLMs presents opportunities for developers to enhance applications continuously. However, this constant adaptation can also lead to performance regressions during model migrations. While several interactive tools have been proposed to streamline the complexity of prompt engineering, few address the specific requirements of regression testing for LLM Migrations. To bridge this gap, we introduce RETAIN (REgression Testing guided LLM migrAtIoN), a tool designed explicitly for regression testing in LLM Migrations. RETAIN comprises two key components: an interactive interface tailored to regression testing needs during LLM migrations, and an error discovery module that facilitates understanding of differences in model behaviors. The error discovery module generates textual descriptions of various errors or differences between model outputs, providing actionable insights for prompt refinement. Our automatic evaluation and empirical user studies demonstrate that RETAIN, when compared to manual evaluation, enabled participants to identify twice as many errors, facilitated experimentation with 75% more prompts, and achieves 12% higher metric scores in a given time frame. |
Preprint |
| Sirius: Contextual Sparsity with Correction for Efficient LLMs | 2024-09-05 | ShowWith the blossom of large language models (LLMs), inference efficiency becomes increasingly important. Various approximation methods are proposed to reduce the cost at inference time. Contextual Sparsity (CS) is appealing for its training-free nature and its ability to reach a higher compression ratio seemingly without quality degradation. However, after a comprehensive evaluation of contextual sparsity methods on various complex generation tasks, we find that although CS succeeds in prompt-understanding tasks, CS significantly degrades the model performance for reasoning, deduction, and knowledge-based tasks. Despite the gap in end-to-end accuracy, we observed that sparse models often share general problem-solving logic and require only a few token corrections to recover the original model performance. This paper introduces Sirius, an efficient correction mechanism, which significantly recovers CS models quality on reasoning tasks while maintaining its efficiency gain. Sirius is evaluated on 6 models with 8 difficult generation tasks in reasoning, math, and coding and shows consistent effectiveness and efficiency. Also, we carefully develop a system implementation for Sirius and show that Sirius achieves roughly 20% reduction in latency for 8B model on-chip and 35% reduction for 70B model offloading. We open-source our implementation of Sirius at https://github.com/Infini-AI-Lab/Sirius.git. |
|
| How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data | 2024-09-05 | ShowRecently, there has been a growing interest in studying how to construct better code instruction tuning data. However, we observe Code models trained with these datasets exhibit high performance on HumanEval but perform worse on other benchmarks such as LiveCodeBench. Upon further investigation, we find that many datasets suffer from severe data leakage. After cleaning up most of the leaked data, some well-known high-quality datasets perform poorly. This discovery reveals a new challenge: identifying which dataset genuinely qualify as high-quality code instruction data. To address this, we propose an efficient code data pruning strategy for selecting good samples. Our approach is based on three dimensions: instruction complexity, response quality, and instruction diversity. Based on our selected data, we present XCoder, a family of models finetuned from LLaMA3. Our experiments show XCoder achieves new state-of-the-art performance using fewer training data, which verify the effectiveness of our data strategy. Moreover, we perform a comprehensive analysis on the data composition and find existing code datasets have different characteristics according to their construction methods, which provide new insights for future code LLMs. Our models and dataset are released in https://github.com/banksy23/XCoder |
Working in progress |
| Planning In Natural Language Improves LLM Search For Code Generation | 2024-09-05 | ShowWhile scaling training compute has led to remarkable improvements in large language models (LLMs), scaling inference compute has not yet yielded analogous gains. We hypothesize that a core missing component is a lack of diverse LLM outputs, leading to inefficient search due to models repeatedly sampling highly similar, yet incorrect generations. We empirically demonstrate that this lack of diversity can be mitigated by searching over candidate plans for solving a problem in natural language. Based on this insight, we propose PLANSEARCH, a novel search algorithm which shows strong results across HumanEval+, MBPP+, and LiveCodeBench (a contamination-free benchmark for competitive coding). PLANSEARCH generates a diverse set of observations about the problem and then uses these observations to construct plans for solving the problem. By searching over plans in natural language rather than directly over code solutions, PLANSEARCH explores a significantly more diverse range of potential solutions compared to baseline search methods. Using PLANSEARCH on top of Claude 3.5 Sonnet achieves a state-of-the-art pass@200 of 77.0% on LiveCodeBench, outperforming both the best score achieved without search (pass@1 = 41.4%) and using standard repeated sampling (pass@200 = 60.6%). Finally, we show that, across all models, search algorithms, and benchmarks analyzed, we can accurately predict performance gains due to search as a direct function of the diversity over generated ideas. |
|
| SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner | 2024-09-05 | ShowJailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the recent indirect and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delays to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM as a defense instance to concurrently protect the target LLM instance in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs (both target and defense LLMs) have the capability to identify harmful prompts or intentions in user queries, which we empirically validate using the commonly used GPT-3.5/4 models across all major jailbreak attacks. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. These models outperform six state-of-the-art defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. We also empirically show that the tuned models are robust to adaptive jailbreaks and prompt injections. |
This ...This paper completes its earlier vision paper, available at arXiv:2402.15727. Updated to the latest analysis and results |
| Perceive, Reflect, and Plan: Designing LLM Agent for Goal-Directed City Navigation without Instructions | 2024-09-05 | ShowThis paper considers a scenario in city navigation: an AI agent is provided with language descriptions of the goal location with respect to some well-known landmarks; By only observing the scene around, including recognizing landmarks and road network connections, the agent has to make decisions to navigate to the goal location without instructions. This problem is very challenging, because it requires agent to establish self-position and acquire spatial representation of complex urban environment, where landmarks are often invisible. In the absence of navigation instructions, such abilities are vital for the agent to make high-quality decisions in long-range city navigation. With the emergent reasoning ability of large language models (LLMs), a tempting baseline is to prompt LLMs to "react" on each observation and make decisions accordingly. However, this baseline has very poor performance that the agent often repeatedly visits same locations and make short-sighted, inconsistent decisions. To address these issues, this paper introduces a novel agentic workflow featured by its abilities to perceive, reflect and plan. Specifically, we find LLaVA-7B can be fine-tuned to perceive the direction and distance of landmarks with sufficient accuracy for city navigation. Moreover, reflection is achieved through a memory mechanism, where past experiences are stored and can be retrieved with current perception for effective decision argumentation. Planning uses reflection results to produce long-term plans, which can avoid short-sighted decisions in long-range navigation. We show the designed workflow significantly improves navigation ability of the LLM agent compared with the state-of-the-art baselines. |
The e...The experiment and dataset are not enough, and we need more experiments to verify our model |
| Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers | 2024-09-05 | ShowIn decoder-based LLMs, the representation of a given layer serves two purposes: as input to the next layer during the computation of the current token; and as input to the attention mechanism of future tokens. In this work, we show that the importance of the latter role might be overestimated. To show that, we start by manipulating the representations of previous tokens; e.g. by replacing the hidden states at some layer k with random vectors. Our experimenting with four LLMs and four tasks show that this operation often leads to small to negligible drop in performance. Importantly, this happens if the manipulation occurs in the top part of the model-k is in the final 30-50% of the layers. In contrast, doing the same manipulation in earlier layers might lead to chance level performance. We continue by switching the hidden state of certain tokens with hidden states of other tokens from another prompt; e.g., replacing the word "Italy" with "France" in "What is the capital of Italy?". We find that when applying this switch in the top 1/3 of the model, the model ignores it (answering "Rome"). However if we apply it before, the model conforms to the switch ("Paris"). Our results hint at a two stage process in transformer-based LLMs: the first part gathers input from previous tokens, while the second mainly processes that information internally. |
|
| LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning | 2024-09-05 | ShowLarge language models (LLMs) have demonstrated significant potential in various tasks, including vulnerability detection. However, current efforts in this area are preliminary, lacking clarity on whether LLMs' vulnerability reasoning capabilities stem from the models themselves or external aids such as knowledge retrieval and tooling support. This paper aims to isolate LLMs' vulnerability reasoning from other capabilities, such as vulnerability knowledge adoption, context information retrieval, and structured output generation. We introduce LLM4Vuln, a unified evaluation framework that separates and assesses LLMs' vulnerability reasoning capabilities and examines improvements when combined with other enhancements. We conducted controlled experiments with 97 ground-truth vulnerabilities and 97 non-vulnerable cases in Solidity and Java, testing them in a total of 9,312 scenarios across four LLMs (GPT-4, GPT-3.5, Mixtral, and Llama 3). Our findings reveal the varying impacts of knowledge enhancement, context supplementation, prompt schemes, and models. Additionally, we identified 14 zero-day vulnerabilities in four pilot bug bounty programs, resulting in $3,576 in bounties. |
This ...This is a technical report by Nanyang Technological University. Updated to support both Solidity and Java |
| 100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances | 2024-09-05 | ShowPredicting the performance of LLMs on individual task instances is essential to ensure their reliability in high-stakes applications. To do so, a possibility is to evaluate the considered LLM on a set of task instances and train an assessor to predict its performance based on features of the instances. However, this approach requires evaluating each new LLM on a sufficiently large set of task instances to train an assessor specific to it. In this work, we leverage the evaluation results of previously tested LLMs to reduce the number of evaluations required to predict the performance of a new LLM. In practice, we propose to test the new LLM on a small set of reference instances and train a generic assessor which predicts the performance of the LLM on an instance based on the performance of the former on the reference set and features of the instance of interest. We conduct empirical studies on HELM-Lite and KindsOfReasoning, a collection of existing reasoning datasets that we introduce, where we evaluate all instruction-fine-tuned OpenAI models until the January 2024 version of GPT4. When predicting performance on instances with the same distribution as those used to train the generic assessor, we find this achieves performance comparable to the LLM-specific assessors trained on the full set of instances. Additionally, we find that randomly selecting the reference instances performs as well as some advanced selection methods we tested. For out of distribution, however, no clear winner emerges and the overall performance is worse, suggesting that the inherent predictability of LLMs is low. |
Prese...Presented at the 2024 KDD workshop on Evaluation and Trustworthiness of Generative AI Models |
| What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering | 2024-09-05 | ShowLarge Language Models (LLMs) changed the way we design and interact with software systems. Their ability to process and extract information from text has drastically improved productivity in a number of routine tasks. Developers that want to include these models in their software stack, however, face a dreadful challenge: debugging LLMs' inconsistent behavior across minor variations of the prompt. We therefore introduce two metrics for classification tasks, namely sensitivity and consistency, which are complementary to task performance. First, sensitivity measures changes of predictions across rephrasings of the prompt, and does not require access to ground truth labels. Instead, consistency measures how predictions vary across rephrasings for elements of the same class. We perform an empirical comparison of these metrics on text classification tasks, using them as guideline for understanding failure modes of the LLM. Our hope is that sensitivity and consistency will be helpful to guide prompt engineering and obtain LLMs that balance robustness with performance. |
|
| From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents | 2024-09-05 | ShowSince the first instances of online education, where courses were uploaded to accessible and shared online platforms, this form of scaling the dissemination of human knowledge to reach a broader audience has sparked extensive discussion and widespread adoption. Recognizing that personalized learning still holds significant potential for improvement, new AI technologies have been continuously integrated into this learning format, resulting in a variety of educational AI applications such as educational recommendation and intelligent tutoring. The emergence of intelligence in large language models (LLMs) has allowed for these educational enhancements to be built upon a unified foundational model, enabling deeper integration. In this context, we propose MAIC (Massive AI-empowered Course), a new form of online education that leverages LLM-driven multi-agent systems to construct an AI-augmented classroom, balancing scalability with adaptivity. Beyond exploring the conceptual framework and technical innovations, we conduct preliminary experiments at Tsinghua University, one of China's leading universities. Drawing from over 100,000 learning records of more than 500 students, we obtain a series of valuable observations and initial analyses. This project will continue to evolve, ultimately aiming to establish a comprehensive open platform that supports and unifies research, technology, and applications in exploring the possibilities of online education in the era of large model AI. We envision this platform as a collaborative hub, bringing together educators, researchers, and innovators to collectively explore the future of AI-driven online education. |
|
| LLM-based event abstraction and integration for IoT-sourced logs | 2024-09-05 | ShowThe continuous flow of data collected by Internet of Things (IoT) devices, has revolutionised our ability to understand and interact with the world across various applications. However, this data must be prepared and transformed into event data before analysis can begin. In this paper, we shed light on the potential of leveraging Large Language Models (LLMs) in event abstraction and integration. Our approach aims to create event records from raw sensor readings and merge the logs from multiple IoT sources into a single event log suitable for further Process Mining applications. We demonstrate the capabilities of LLMs in event abstraction considering a case study for IoT application in elderly care and longitudinal health monitoring. The results, showing on average an accuracy of 90% in detecting high-level activities. These results highlight LLMs' promising potential in addressing event abstraction and integration challenges, effectively bridging the existing gap. |
12 pages |
| Rx Strategist: Prescription Verification using LLM Agents System | 2024-09-05 | ShowTo protect patient safety, modern pharmaceutical complexity demands strict prescription verification. We offer a new approach - Rx Strategist - that makes use of knowledge graphs and different search strategies to enhance the power of Large Language Models (LLMs) inside an agentic framework. This multifaceted technique allows for a multi-stage LLM pipeline and reliable information retrieval from a custom-built active ingredient database. Different facets of prescription verification, such as indication, dose, and possible drug interactions, are covered in each stage of the pipeline. We alleviate the drawbacks of monolithic LLM techniques by spreading reasoning over these stages, improving correctness and reliability while reducing memory demands. Our findings demonstrate that Rx Strategist surpasses many current LLMs, achieving performance comparable to that of a highly experienced clinical pharmacist. In the complicated world of modern medications, this combination of LLMs with organized knowledge and sophisticated search methods presents a viable avenue for reducing prescription errors and enhancing patient outcomes. |
17 Pa...17 Pages, 6 Figures, Under Review |
| Hardware Acceleration of LLMs: A comprehensive survey and comparison | 2024-09-05 | ShowLarge Language Models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. In this paper, we present a comprehensive survey of the several research efforts that have been presented for the acceleration of transformer networks for Large Language Models using hardware accelerators. The survey presents the frameworks that have been proposed and then performs a qualitative and quantitative comparison regarding the technology, the processing platform (FPGA, ASIC, In-Memory, GPU), the speedup, the energy efficiency, the performance (GOPs), and the energy efficiency (GOPs/W) of each framework. The main challenge in comparison is that every proposed scheme is implemented on a different process technology making hard a fair comparison. The main contribution of this paper is that we extrapolate the results of the performance and the energy efficiency on the same technology to make a fair comparison; one theoretical and one more practical. We implement part of the LLMs on several FPGA chips to extrapolate the results to the same process technology and then we make a fair comparison of the performance. |
|
| Sketch: A Toolkit for Streamlining LLM Operations | 2024-09-05 | ShowLarge language models (LLMs) represented by GPT family have achieved remarkable success. The characteristics of LLMs lie in their ability to accommodate a wide range of tasks through a generative approach. However, the flexibility of their output format poses challenges in controlling and harnessing the model's outputs, thereby constraining the application of LLMs in various domains. In this work, we present Sketch, an innovative toolkit designed to streamline LLM operations across diverse fields. Sketch comprises the following components: (1) a suite of task description schemas and prompt templates encompassing various NLP tasks; (2) a user-friendly, interactive process for building structured output LLM services tailored to various NLP tasks; (3) an open-source dataset for output format control, along with tools for dataset construction; and (4) an open-source model based on LLaMA3-8B-Instruct that adeptly comprehends and adheres to output formatting instructions. We anticipate this initiative to bring considerable convenience to LLM users, achieving the goal of ''plug-and-play'' for various applications. The components of Sketch will be progressively open-sourced at https://github.com/cofe-ai/Sketch. |
|
| Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models? | 2024-09-05 | ShowThe significant advancements of Large Language Models (LLMs) in generative tasks have led to a growing body of work exploring LLM-based embedding models. While these models, employing different pooling and attention strategies, have achieved state-of-the-art performance on public embedding benchmarks, questions still arise about what constitutes an effective design for LLM-based embedding models. However, these models are often trained on different datasets, using different LLM base models or training settings. Moreover, evaluations on public embedding benchmarks often fail to report statistical significance, making it difficult to determine which designs truly contribute to final performance. This complicates the process for practitioners seeking optimal training recipes for LLM-based embedding models. In this study, we conduct a large-scale experiment by training a series of LLM-based embedding models using the same training data and base model but differing in their pooling and attention strategies. The results show that there is no one-size-fits-all solution: while bidirectional attention and an additional trainable pooling layer outperform in text similarity and information retrieval tasks, they do not significantly surpass simpler designs like EOS-last token pooling and default causal attention in clustering and classification tasks. Furthermore, we propose a new pooling strategy, Multi-Layers Trainable Pooling, which transforms the outputs of all hidden layers, rather than just the last layer, using a cross-attention network. This method proves to be statistically superior in text similarity and retrieval tasks compared to existing pooling methods. Overall, this paper sheds light on effective training strategies for LLM-based embedding models. |
|
| LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts | 2024-09-05 | ShowWith the emergence of widely available powerful LLMs, disinformation generated by large Language Models (LLMs) has become a major concern. Historically, LLM detectors have been touted as a solution, but their effectiveness in the real world is still to be proven. In this paper, we focus on an important setting in information operations -- short news-like posts generated by moderately sophisticated attackers. We demonstrate that existing LLM detectors, whether zero-shot or purpose-trained, are not ready for real-world use in that setting. All tested zero-shot detectors perform inconsistently with prior benchmarks and are highly vulnerable to sampling temperature increase, a trivial attack absent from recent benchmarks. A purpose-trained detector generalizing across LLMs and unseen attacks can be developed, but it fails to generalize to new human-written texts. We argue that the former indicates domain-specific benchmarking is needed, while the latter suggests a trade-off between the adversarial evasion resilience and overfitting to the reference human text, with both needing evaluation in benchmarks and currently absent. We believe this suggests a re-consideration of current LLM detector benchmarking approaches and provides a dynamically extensible benchmark to allow it (https://github.com/Reliable-Information-Lab-HEVS/dynamic_llm_detector_benchmark). |
20 pa...20 pages, 7 tables, 13 figures, under consideration for EMNLP |
| Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation | 2024-09-05 | ShowThe Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs). However, despite their widespread adoption and success, CoT methods often exhibit instability due to their inability to consistently ensure the quality of generated reasoning paths, leading to sub-optimal reasoning performance. To address this challenge, we propose the \textbf{Strategic Chain-of-Thought} (SCoT), a novel methodology designed to refine LLM performance by integrating strategic knowledge prior to generating intermediate reasoning steps. SCoT employs a two-stage approach within a single prompt: first eliciting an effective problem-solving strategy, which is then used to guide the generation of high-quality CoT paths and final answers. Our experiments across eight challenging reasoning datasets demonstrate significant improvements, including a 21.05% increase on the GSM8K dataset and 24.13% on the Tracking_Objects dataset, respectively, using the Llama3-8b model. Additionally, we extend the SCoT framework to develop a few-shot method with automatically matched demonstrations, yielding even stronger results. These findings underscore the efficacy of SCoT, highlighting its potential to substantially enhance LLM performance in complex reasoning tasks. |
|
| Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard | 2024-09-05 | ShowThis paper conducts a longitudinal study over eleven months to address the limitations of prior research on the Open Ko-LLM Leaderboard, which have relied on empirical studies with restricted observation periods of only five months. By extending the analysis duration, we aim to provide a more comprehensive understanding of the progression in developing Korean large language models (LLMs). Our study is guided by three primary research questions: (1) What are the specific challenges in improving LLM performance across diverse tasks on the Open Ko-LLM Leaderboard over time? (2) How does model size impact task performance correlations across various benchmarks? (3) How have the patterns in leaderboard rankings shifted over time on the Open Ko-LLM Leaderboard?. By analyzing 1,769 models over this period, our research offers a comprehensive examination of the ongoing advancements in LLMs and the evolving nature of evaluation frameworks. |
|
| End User Authoring of Personalized Content Classifiers: Comparing Example Labeling, Rule Writing, and LLM Prompting | 2024-09-05 | ShowExisting tools for laypeople to create personal classifiers often assume a motivated user working uninterrupted in a single, lengthy session. However, users tend to engage with social media casually, with many short sessions on an ongoing, daily basis. To make creating personal classifiers for content curation easier for such users, tools should support rapid initialization and iterative refinement. In this work, we compare three strategies -- (1) example labeling, (2) rule writing, and (3) large language model (LLM) prompting -- for end users to build personal content classifiers. From an experiment with 37 non-programmers tasked with creating personalized comment moderation filters, we found that with LLM prompting, participants reached 95% of peak performance in 5 minutes, beating other strategies due to higher recall, but all strategies struggled with iterative refinement. Despite LLM prompting's better performance, participants preferred different strategies in different contexts and, even when prompting, provided examples or wrote rule-like prompts, suggesting hybrid approaches. |
|
| Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration | 2024-09-05 | ShowBlack-box large language models (LLMs) are increasingly deployed in various environments, making it essential for these models to effectively convey their confidence and uncertainty, especially in high-stakes settings. However, these models often exhibit overconfidence, leading to potential risks and misjudgments. Existing techniques for eliciting and calibrating LLM confidence have primarily focused on general reasoning datasets, yielding only modest improvements. Accurate calibration is crucial for informed decision-making and preventing adverse outcomes but remains challenging due to the complexity and variability of tasks these models perform. In this work, we investigate the miscalibration behavior of black-box LLMs within the healthcare setting. We propose a novel method, \textit{Atypical Presentations Recalibration}, which leverages atypical presentations to adjust the model's confidence estimates. Our approach significantly improves calibration, reducing calibration errors by approximately 60% on three medical question answering datasets and outperforming existing methods such as vanilla verbalized confidence, CoT verbalized confidence and others. Additionally, we provide an in-depth analysis of the role of atypicality within the recalibration framework. |
|
| Content Moderation by LLM: From Accuracy to Legitimacy | 2024-09-05 | ShowOne trending application of LLM (large language model) is to use it for content moderation in online platforms. Most current studies on this application have focused on the metric of accuracy - the extent to which LLM makes correct decisions about content. This article argues that accuracy is insufficient and misleading, because it fails to grasp the distinction between easy cases and hard cases as well as the inevitable trade-offs in achieving higher accuracy. Closer examination reveals that content moderation is a constitutive part of platform governance, the key of which is to gain and enhance legitimacy. Instead of making moderation decisions correct, the chief goal of LLM is to make them legitimate. In this regard, this article proposes a paradigm shift from the single benchmark of accuracy towards a legitimacy-based framework of evaluating the performance of LLM moderators. The framework suggests that for easy cases, the key is to ensure accuracy, speed and transparency, while for hard cases, what matters is reasoned justification and user participation. Examined under this framework, LLM's real potential in moderation is not accuracy improvement. Rather, LLM can better contribute in four other aspects: to conduct screening of hard cases from easy cases, to provide quality explanations for moderation decisions, to assist human reviewers in getting more contextual information, and to facilitate user participation in a more interactive way. Using normative theories from law and social sciences to critically assess the new technological application, this article seeks to redefine LLM's role in content moderation and redirect relevant research in this field. |
|
| Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation | 2024-09-05 | ShowLarge language models (LLMs) have achieved state-of-the-art performance in various language processing tasks, motivating their adoption in simultaneous translation. Current fine-tuning methods to adapt LLMs for simultaneous translation focus on prompting optimization strategies using either data augmentation or prompt structure modifications. However, these methods suffer from several issues, such as unnecessarily expanded training sets, computational inefficiency from dumping the key and value cache, increased prompt sizes, or restriction to a single decision policy. To eliminate these issues, in this work, we propose SimulMask, a new paradigm for fine-tuning LLMs for simultaneous translation. It utilizes a novel attention mask approach that models simultaneous translation during fine-tuning by masking attention for a desired decision policy. Applying the proposed SimulMask on a Falcon LLM for the IWSLT 2017 dataset, we have observed a significant translation quality improvement compared to state-of-the-art prompting optimization strategies on five language pairs while reducing the computational cost. |
|
| Multi-language Unit Test Generation using LLMs | 2024-09-04 | ShowImplementing automated unit tests is an important but time consuming activity in software development. Developers dedicate substantial time to writing tests for validating an application and preventing regressions. To support developers in this task, software engineering research over the past few decades has developed many techniques for automating unit test generation. However, despite this effort, usable tools exist for very few programming languages -- mainly Java, C, and C# and, more recently, for Python. Moreover, studies have found that automatically generated tests suffer poor readability and often do not resemble developer-written tests. In this work, we present a rigorous investigation of how large language models (LLMs) can help bridge the gap. We describe a generic pipeline that incorporates static analysis to guide LLMs in generating compilable and high-coverage test cases. We illustrate how the pipeline can be applied to different programming languages, specifically Java and Python, and to complex software requiring environment mocking. We conducted a through empirical study to assess the quality of the generated tests in terms of coverage, mutation score, and test naturalness -- evaluating them on standard as well as enterprise Java applications and a large Python benchmark. Our results demonstrate that LLM-based test generation, when guided by static analysis, can be competitive with, and even outperform, state-of-the-art test-generation techniques in coverage achieved while also producing considerably more natural test cases that developers find easy to read and understand. We also present the results of a user study, conducted with 161 professional developers, that highlights the naturalness characteristics of the tests generated by our approach. |
|
| A Comparative Study of Offline Models and Online LLMs in Fake News Detection | 2024-09-04 | ShowFake news detection remains a critical challenge in today's rapidly evolving digital landscape, where misinformation can spread faster than ever before. Traditional fake news detection models often rely on static datasets and auxiliary information, such as metadata or social media interactions, which limits their adaptability to real-time scenarios. Recent advancements in Large Language Models (LLMs) have demonstrated significant potential in addressing these challenges due to their extensive pre-trained knowledge and ability to analyze textual content without relying on auxiliary data. However, many of these LLM-based approaches are still rooted in static datasets, with limited exploration into their real-time processing capabilities. This paper presents a systematic evaluation of both traditional offline models and state-of-the-art LLMs for real-time fake news detection. We demonstrate the limitations of existing offline models, including their inability to adapt to dynamic misinformation patterns. Furthermore, we show that newer LLM models with online capabilities, such as GPT-4, Claude, and Gemini, are better suited for detecting emerging fake news in real-time contexts. Our findings emphasize the importance of transitioning from offline to online LLM models for real-time fake news detection. Additionally, the public accessibility of LLMs enhances their scalability and democratizes the tools needed to combat misinformation. By leveraging real-time data, our work marks a significant step toward more adaptive, effective, and scalable fake news detection systems. |
|
| Learning to Ask: When LLMs Meet Unclear Instruction | 2024-09-04 | ShowEquipped with the capability to call functions, modern large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone. However, the effective execution of these tools relies heavily not just on the advanced capabilities of LLMs but also on precise user instructions, which often cannot be ensured in the real world. To evaluate the performance of LLMs tool-use under imperfect instructions, we meticulously examine the real-world instructions queried from users, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench (NoisyToolBench). We find that due to the next-token prediction training objective, LLMs tend to arbitrarily generate the missed argument, which may lead to hallucinations and risks. To address this issue, we propose a novel framework, Ask-when-Needed (AwN), which prompts LLMs to ask questions to users whenever they encounter obstacles due to unclear instructions. Moreover, to reduce the manual labor involved in user-LLM interaction and assess LLMs performance in tool utilization from both accuracy and efficiency perspectives, we design an automated evaluation tool named ToolEvaluator. Our experiments demonstrate that the AwN significantly outperforms existing frameworks for tool learning in the NoisyToolBench. We will release all related code and datasets to support future research. |
|
| GenAI-powered Multi-Agent Paradigm for Smart Urban Mobility: Opportunities and Challenges for Integrating Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) with Intelligent Transportation Systems | 2024-09-04 | ShowLeveraging recent advances in generative AI, multi-agent systems are increasingly being developed to enhance the functionality and efficiency of smart city applications. This paper explores the transformative potential of large language models (LLMs) and emerging Retrieval-Augmented Generation (RAG) technologies in Intelligent Transportation Systems (ITS), paving the way for innovative solutions to address critical challenges in urban mobility. We begin by providing a comprehensive overview of the current state-of-the-art in mobility data, ITS, and Connected Vehicles (CV) applications. Building on this review, we discuss the rationale behind RAG and examine the opportunities for integrating these Generative AI (GenAI) technologies into the smart mobility sector. We propose a conceptual framework aimed at developing multi-agent systems capable of intelligently and conversationally delivering smart mobility services to urban commuters, transportation operators, and decision-makers. Our approach seeks to foster an autonomous and intelligent approach that (a) promotes science-based advisory to reduce traffic congestion, accidents, and carbon emissions at multiple scales, (b) facilitates public education and engagement in participatory mobility management, and (c) automates specialized transportation management tasks and the development of critical ITS platforms, such as data analytics and interpretation, knowledge representation, and traffic simulations. By integrating LLM and RAG, our approach seeks to overcome the limitations of traditional rule-based multi-agent systems, which rely on fixed knowledge bases and limited reasoning capabilities. This integration paves the way for a more scalable, intuitive, and automated multi-agent paradigm, driving advancements in ITS and urban mobility. |
|
| NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls | 2024-09-04 | ShowAutonomous agent applications powered by large language models (LLMs) have recently risen to prominence as effective tools for addressing complex real-world tasks. At their core, agentic workflows rely on LLMs to plan and execute the use of tools and external Application Programming Interfaces (APIs) in sequence to arrive at the answer to a user's request. Various benchmarks and leaderboards have emerged to evaluate an LLM's capabilities for tool and API use; however, most of these evaluations only track single or multiple isolated API calling capabilities. In this paper, we present NESTFUL, a benchmark to evaluate LLMs on nested sequences of API calls, i.e., sequences where the output of one API call is passed as input to a subsequent call. NESTFUL has a total of 300 human annotated samples divided into two types - executable and non-executable. The executable samples are curated manually by crawling Rapid-APIs whereas the non-executable samples are hand picked by human annotators from data synthetically generated using an LLM. We evaluate state-of-the-art LLMs with function calling abilities on NESTFUL. Our results show that most models do not perform well on nested APIs in NESTFUL as compared to their performance on the simpler problem settings available in existing benchmarks. |
|
| Configurable Foundation Models: Building LLMs from a Modular Perspective | 2024-09-04 | ShowAdvancements in LLMs have recently unveiled challenges tied to computational efficiency and continual scalability due to their requirements of huge parameters, making the applications and evolution of these models on devices with limited computation resources and scenarios requiring various abilities increasingly cumbersome. Inspired by modularity within the human brain, there is a growing tendency to decompose LLMs into numerous functional modules, allowing for inference with part of modules and dynamic assembly of modules to tackle complex tasks, such as mixture-of-experts. To highlight the inherent efficiency and composability of the modular approach, we coin the term brick to represent each functional module, designating the modularized structure as configurable foundation models. In this paper, we offer a comprehensive overview and investigation of the construction, utilization, and limitation of configurable foundation models. We first formalize modules into emergent bricks - functional neuron partitions that emerge during the pre-training phase, and customized bricks - bricks constructed via additional post-training to improve the capabilities and knowledge of LLMs. Based on diverse functional bricks, we further present four brick-oriented operations: retrieval and routing, merging, updating, and growing. These operations allow for dynamic configuration of LLMs based on instructions to handle complex tasks. To verify our perspective, we conduct an empirical analysis on widely-used LLMs. We find that the FFN layers follow modular patterns with functional specialization of neurons and functional neuron partitions. Finally, we highlight several open issues and directions for future research. Overall, this paper aims to offer a fresh modular perspective on existing LLM research and inspire the future creation of more efficient and scalable foundational models. |
|
| The Design of an LLM-powered Unstructured Analytics System | 2024-09-04 | ShowLLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the design of an unstructured analytics system, Aryn, and the tenets and use cases that motivate its design. With Aryn, users can specify queries in natural language and the system automatically determines a semantic plan and executes it to compute an answer from a large collection of unstructured documents using LLMs. At the core of Aryn is Sycamore, a declarative document processing engine, built using Ray, that provides a reliable distributed abstraction called DocSets. Sycamore allows users to analyze, enrich, and transform complex documents at scale. Aryn also comprises Luna, a query planner that translates natural language queries to Sycamore scripts, and the Aryn Partitioner, which takes raw PDFs and document images, and converts them to DocSets for downstream processing. Using Aryn, we demonstrate a real world use case for analyzing accident reports from the National Transportation Safety Board (NTSB), and discuss some of the major challenges we encountered in deploying Aryn in the wild. |
6 pag...6 pages, 3 figures, fixed typos |
| Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms | 2024-09-04 | ShowLarge language models (LLMs) are trained on broad corpora and then used in communities with specialized norms. Is providing LLMs with community rules enough for models to follow these norms? We evaluate LLMs' capacity to detect (Task 1) and correct (Task 2) biased Wikipedia edits according to Wikipedia's Neutral Point of View (NPOV) policy. LLMs struggled with bias detection, achieving only 64% accuracy on a balanced dataset. Models exhibited contrasting biases (some under- and others over-predicted bias), suggesting distinct priors about neutrality. LLMs performed better at generation, removing 79% of words removed by Wikipedia editors. However, LLMs made additional changes beyond Wikipedia editors' simpler neutralizations, resulting in high-recall but low-precision editing. Interestingly, crowdworkers rated AI rewrites as more neutral (70%) and fluent (61%) than Wikipedia-editor rewrites. Qualitative analysis found LLMs sometimes applied NPOV more comprehensively than Wikipedia editors but often made extraneous non-NPOV-related changes (such as grammar). LLMs may apply rules in ways that resonate with the public but diverge from community experts. While potentially effective for generation, LLMs may reduce editor agency and increase moderation workload (e.g., verifying additions). Even when rules are easy to articulate, having LLMs apply them like community members may still be difficult. |
|
| Hallucination Detection in LLMs: Fast and Memory-Efficient Finetuned Models | 2024-09-04 | ShowUncertainty estimation is a necessary component when implementing AI in high-risk settings, such as autonomous cars, medicine, or insurances. Large Language Models (LLMs) have seen a surge in popularity in recent years, but they are subject to hallucinations, which may cause serious harm in high-risk settings. Despite their success, LLMs are expensive to train and run: they need a large amount of computations and memory, preventing the use of ensembling methods in practice. In this work, we present a novel method that allows for fast and memory-friendly training of LLM ensembles. We show that the resulting ensembles can detect hallucinations and are a viable approach in practice as only one GPU is needed for training and inference. |
5 pages, 3 figures |
| LLM-Assisted Visual Analytics: Opportunities and Challenges | 2024-09-04 | ShowWe explore the integration of large language models (LLMs) into visual analytics (VA) systems to transform their capabilities through intuitive natural language interactions. We survey current research directions in this emerging field, examining how LLMs are integrated into data management, language interaction, visualisation generation, and language generation processes. We highlight the new possibilities that LLMs bring to VA, especially how they can change VA processes beyond the usual use cases. We especially highlight building new visualisation-language models, allowing access of a breadth of domain knowledge, multimodal interaction, and opportunities with guidance. Finally, we carefully consider the prominent challenges of using current LLMs in VA tasks. Our discussions in this paper aim to guide future researchers working on LLM-assisted VA systems and help them navigate common obstacles when developing these systems. |
Accep...Accepted at EG UK Computer Graphics & Visual Computing 2024 |
| Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs | 2024-09-04 | ShowLarge Language Models (LLMs) have demonstrated remarkable efficiency in tackling various tasks based on human instructions, but recent studies reveal that these models often fail to achieve satisfactory results on questions involving reasoning, such as mathematics or physics questions. This phenomenon is usually attributed to the uncertainty regarding whether these models could genuinely comprehend the knowledge embedded in the text or merely learn to replicate the token distribution without a true understanding of the content. In this paper, we delve into this problem and aim to enhance the reasoning capabilities of LLMs. First, we investigate if the model has genuine reasoning capabilities by visualizing the text generation process at the attention and representation level. Then, we formulate the reasoning process of LLMs into a causal framework, which provides a formal explanation of the problems we observe in the visualization. Finally, building upon this causal framework, we propose Deconfounded Causal Adaptation (DCA), a novel parameter-efficient fine-tuning (PEFT) method to enhance the model's reasoning capabilities by encouraging the model to extract the general problem-solving skills and apply these skills to different questions. Experiments show that our method outperforms the baseline consistently across multiple benchmarks, and with only 1.2M tunable parameters, we achieve better or comparable results to other fine-tuning methods. This demonstrates the effectiveness and efficiency of our method in improving the overall accuracy and reliability of LLMs. |
|
| Hypothesizing Missing Causal Variables with LLMs | 2024-09-04 | ShowScientific discovery is a catalyst for human intellectual advances, driven by the cycle of hypothesis generation, experimental design, data evaluation, and iterative assumption refinement. This process, while crucial, is expensive and heavily dependent on the domain knowledge of scientists to generate hypotheses and navigate the scientific cycle. Central to this is causality, the ability to establish the relationship between the cause and the effect. Motivated by the scientific discovery process, in this work, we formulate a novel task where the input is a partial causal graph with missing variables, and the output is a hypothesis about the missing variables to complete the partial graph. We design a benchmark with varying difficulty levels and knowledge assumptions about the causal graph. With the growing interest in using Large Language Models (LLMs) to assist in scientific discovery, we benchmark open-source and closed models on our testbed. We show the strong ability of LLMs to hypothesize the mediation variables between a cause and its effect. In contrast, they underperform in hypothesizing the cause and effect variables themselves. We also observe surprising results where some of the open-source models outperform the closed GPT-4 model. |
Code ...Code - https://github.com/ivaxi0s/hypothesizing-causal-variable-llm |
| Prompt Compression with Context-Aware Sentence Encoding for Fast and Improved LLM Inference | 2024-09-04 | ShowLarge language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question. Token-based removal methods are one of the most prominent approaches in this direction, but risk losing the semantics of the context caused by intermediate token removal, especially under high compression ratios, while also facing challenges in computational efficiency. In this work, we propose context-aware prompt compression (CPC), a sentence-level prompt compression technique where its key innovation is a novel context-aware sentence encoder that provides a relevance score for each sentence for a given question. To train this encoder, we generate a new dataset consisting of questions, positives, and negative pairs where positives are sentences relevant to the question, while negatives are irrelevant context sentences. We train the encoder in a contrastive setup to learn context-aware sentence representations. Our method considerably outperforms prior works on prompt compression on benchmark datasets and is up to 10.93x faster at inference compared to the best token-level compression method. We also find better improvement for shorter length constraints in most benchmarks, showing the effectiveness of our proposed solution in the compression of relevant information in a shorter context. Finally, we release the code and the dataset for quick reproducibility and further development: https://github.com/Workday/cpc. |
|
| SparQ Attention: Bandwidth-Efficient LLM Inference | 2024-09-04 | ShowThe computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically causes token-generation to be bottlenecked by data transfer. For this reason, we introduce SparQ Attention, a technique for increasing the inference throughput of LLMs by utilising memory bandwidth more efficiently within the attention layers, through selective fetching of the cached history. Our proposed technique can be applied directly to off-the-shelf LLMs during inference, without requiring any modification to the pre-training setup or additional fine-tuning. We show that SparQ Attention brings up to 8x savings in attention data transfers without substantial drops in accuracy, by evaluating Llama 2 and 3, Mistral, Gemma and Pythia models on a wide range of downstream tasks. |
|
| Towards Measuring and Modeling "Culture" in LLMs: A Survey | 2024-09-04 | ShowWe present a survey of more than 90 recent papers that aim to study cultural representation and inclusion in large language models (LLMs). We observe that none of the studies explicitly define "culture, which is a complex, multifaceted concept; instead, they probe the models on some specially designed datasets which represent certain aspects of "culture". We call these aspects the proxies of culture, and organize them across two dimensions of demographic and semantic proxies. We also categorize the probing methods employed. Our analysis indicates that only certain aspects of ``culture,'' such as values and objectives, have been studied, leaving several other interesting and important facets, especially the multitude of semantic domains (Thompson et al., 2020) and aboutness (Hershcovich et al., 2022), unexplored. Two other crucial gaps are the lack of robustness of probing techniques and situated studies on the impact of cultural mis- and under-representation in LLM-based applications. |
|
| Can AI Replace Human Subjects? A Large-Scale Replication of Psychological Experiments with LLMs | 2024-09-04 | ShowArtificial Intelligence (AI) is increasingly being integrated into scientific research, particularly in the social sciences, where understanding human behavior is critical. Large Language Models (LLMs) like GPT-4 have shown promise in replicating human-like responses in various psychological experiments. However, the extent to which LLMs can effectively replace human subjects across diverse experimental contexts remains unclear. Here, we conduct a large-scale study replicating 154 psychological experiments from top social science journals with 618 main effects and 138 interaction effects using GPT-4 as a simulated participant. We find that GPT-4 successfully replicates 76.0 percent of main effects and 47.0 percent of interaction effects observed in the original studies, closely mirroring human responses in both direction and significance. However, only 19.44 percent of GPT-4's replicated confidence intervals contain the original effect sizes, with the majority of replicated effect sizes exceeding the 95 percent confidence interval of the original studies. Additionally, there is a 71.6 percent rate of unexpected significant results where the original studies reported null findings, suggesting potential overestimation or false positives. Our results demonstrate the potential of LLMs as powerful tools in psychological research but also emphasize the need for caution in interpreting AI-driven findings. While LLMs can complement human studies, they cannot yet fully replace the nuanced insights provided by human subjects. |
5 figures, 2 tables |
| Scaling Laws for Economic Productivity: Experimental Evidence in LLM-Assisted Translation | 2024-09-04 | ShowThis paper derives 'scaling laws' -- empirical relationships between the amount of training compute used for a Large Language Model (LLM) and its performance -- for economic outcomes. In a preregistered experiment, 300 professional translators completed 1800 tasks with access to one of thirteen LLMs with differing model training compute sizes (or a control). Our results show that model scaling substantially raises productivity: for every 10x increase in model compute, translators completed tasks 12.3% quicker, received 0.18 s.d. higher grades, and earned 16.1% more per minute (including bonus payments). Further, the gains from model scaling are much higher for lower-skilled workers who gain a 4x larger improvement in task completion speed. These results imply further frontier model scaling -- which is currently estimated at 4x increase per year -- may have significant economic implications. |
| Title | Date | Abstract | Comment |
|---|---|---|---|
| Lightweight Multiscale Feature Fusion Super-Resolution Network Based on Two-branch Convolution and Transformer | 2024-09-10 | ShowThe single image super-resolution(SISR) algorithms under deep learning currently have two main models, one based on convolutional neural networks and the other based on Transformer. The former uses the stacking of convolutional layers with different convolutional kernel sizes to design the model, which enables the model to better extract the local features of the image; the latter uses the self-attention mechanism to design the model, which allows the model to establish long-distance dependencies between image pixel points through the self-attention mechanism and then better extract the global features of the image. However, both of the above methods face their problems. Based on this, this paper proposes a new lightweight multi-scale feature fusion network model based on two-way complementary convolutional and Transformer, which integrates the respective features of Transformer and convolutional neural networks through a two-branch network architecture, to realize the mutual fusion of global and local information. Meanwhile, considering the partial loss of information caused by the low-pixel images trained by the deep neural network, this paper designs a modular connection method of multi-stage feature supplementation to fuse the feature maps extracted from the shallow stage of the model with those extracted from the deep stage of the model, to minimize the loss of the information in the feature images that is beneficial to the image restoration as much as possible, to facilitate the obtaining of a higher-quality restored image. The practical results finally show that the model proposed in this paper is optimal in image recovery performance when compared with other lightweight models with the same amount of parameters. |
11 pages,12 figures |
| Multi-Weather Image Restoration via Histogram-Based Transformer Feature Enhancement | 2024-09-10 | ShowCurrently, the mainstream restoration tasks under adverse weather conditions have predominantly focused on single-weather scenarios. However, in reality, multiple weather conditions always coexist and their degree of mixing is usually unknown. Under such complex and diverse weather conditions, single-weather restoration models struggle to meet practical demands. This is particularly critical in fields such as autonomous driving, where there is an urgent need for a model capable of effectively handling mixed weather conditions and enhancing image quality in an automated manner. In this paper, we propose a Task Sequence Generator module that, in conjunction with the Task Intra-patch Block, effectively extracts task-specific features embedded in degraded images. The Task Intra-patch Block introduces an external learnable sequence that aids the network in capturing task-specific information. Additionally, we employ a histogram-based transformer module as the backbone of our network, enabling the capture of both global and local dynamic range features. Our proposed model achieves state-of-the-art performance on public datasets. |
arXiv...arXiv admin note: text overlap with arXiv:2409.03249 |
| AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration | 2024-09-10 | ShowImage Transformers show a magnificent success in Image Restoration tasks. Nevertheless, most of transformer-based models are strictly bounded by exorbitant memory occupancy. Our goal is to reduce the memory consumption of Swin Transformer and at the same time speed up the model during training process. Thus, we introduce AgileIR, group shifted attention mechanism along with window attention, which sparsely simplifies the model in architecture. We propose Group Shifted Window Attention (GSWA) to decompose Shift Window Multi-head Self Attention (SW-MSA) and Window Multi-head Self Attention (W-MSA) into groups across their attention heads, contributing to shrinking memory usage in back propagation. In addition to that, we keep shifted window masking and its shifted learnable biases during training, in order to induce the model interacting across windows within the channel. We also re-allocate projection parameters to accelerate attention matrix calculation, which we found a negligible decrease in performance. As a result of experiment, compared with our baseline SwinIR and other efficient quantization models, AgileIR keeps the performance still at 32.20 dB on Set5 evaluation dataset, exceeding other methods with tailor-made efficient methods and saves over 50% memory while a large batch size is employed. |
|
| Adversarial Purification and Fine-tuning for Robust UDC Image Restoration | 2024-09-08 | ShowThis study delves into the enhancement of Under-Display Camera (UDC) image restoration models, focusing on their robustness against adversarial attacks. Despite its innovative approach to seamless display integration, UDC technology faces unique image degradation challenges exacerbated by the susceptibility to adversarial perturbations. Our research initially conducts an in-depth robustness evaluation of deep-learning-based UDC image restoration models by employing several white-box and black-box attacking methods. This evaluation is pivotal in understanding the vulnerabilities of current UDC image restoration techniques. Following the assessment, we introduce a defense framework integrating adversarial purification with subsequent fine-tuning processes. First, our approach employs diffusion-based adversarial purification, effectively neutralizing adversarial perturbations. Then, we apply the fine-tuning methodologies to refine the image restoration models further, ensuring that the quality and fidelity of the restored images are maintained. The effectiveness of our proposed approach is validated through extensive experiments, showing marked improvements in resilience against typical adversarial attacks. |
|
| Power Line Aerial Image Restoration under dverse Weather: Datasets and Baselines | 2024-09-07 | ShowPower Line Autonomous Inspection (PLAI) plays a crucial role in the construction of smart grids due to its great advantages of low cost, high efficiency, and safe operation. PLAI is completed by accurately detecting the electrical components and defects in the aerial images captured by Unmanned Aerial Vehicles (UAVs). However, the visible quality of aerial images is inevitably degraded by adverse weather like haze, rain, or snow, which are found to drastically decrease the detection accuracy in our research. To circumvent this problem, we propose a new task of Power Line Aerial Image Restoration under Adverse Weather (PLAIR-AW), which aims to recover clean and high-quality images from degraded images with bad weather thus improving detection performance for PLAI. In this context, we are the first to release numerous corresponding datasets, namely, HazeCPLID, HazeTTPLA, HazeInsPLAD for power line aerial image dehazing, RainCPLID, RainTTPLA, RainInsPLAD for power line aerial image deraining, SnowCPLID, SnowInsPLAD for power line aerial image desnowing, which are synthesized upon the public power line aerial image datasets of CPLID, TTPLA, InsPLAD following the mathematical models. Meanwhile, we select numerous state-of-the-art methods from image restoration community as the baseline methods for PLAIR-AW. At last, we conduct large-scale empirical experiments to evaluate the performance of baseline methods on the proposed datasets. The proposed datasets and trained models are available at https://github.com/ntuhubin/PLAIR-AW. |
|
| Empirical Bayesian image restoration by Langevin sampling with a denoising diffusion implicit prior | 2024-09-06 | ShowScore-based diffusion methods provide a powerful strategy to solve image restoration tasks by flexibly combining a pre-trained foundational prior model with a likelihood function specified during test time. Such methods are predominantly derived from two stochastic processes: reversing Ornstein-Uhlenbeck, which underpins the celebrated denoising diffusion probabilistic models (DDPM) and denoising diffusion implicit models (DDIM), and the Langevin diffusion process. The solutions delivered by DDPM and DDIM are often remarkably realistic, but they are not always consistent with measurements because of likelihood intractability issues and the associated required approximations. Alternatively, using a Langevin process circumvents the intractable likelihood issue, but usually leads to restoration results of inferior quality and longer computing times. This paper presents a novel and highly computationally efficient image restoration method that carefully embeds a foundational DDPM denoiser within an empirical Bayesian Langevin algorithm, which jointly calibrates key model hyper-parameters as it estimates the model's posterior mean. Extensive experimental results on three canonical tasks (image deblurring, super-resolution, and inpainting) demonstrate that the proposed approach improves on state-of-the-art strategies both in image estimation accuracy and computing time. |
24 pages |
| Data-free Distillation with Degradation-prompt Diffusion for Multi-weather Image Restoration | 2024-09-05 | ShowMulti-weather image restoration has witnessed incredible progress, while the increasing model capacity and expensive data acquisition impair its applications in memory-limited devices. Data-free distillation provides an alternative for allowing to learn a lightweight student model from a pre-trained teacher model without relying on the original training data. The existing data-free learning methods mainly optimize the models with the pseudo data generated by GANs or the real data collected from the Internet. However, they inevitably suffer from the problems of unstable training or domain shifts with the original data. In this paper, we propose a novel Data-free Distillation with Degradation-prompt Diffusion framework for multi-weather Image Restoration (D4IR). It replaces GANs with pre-trained diffusion models to avoid model collapse and incorporates a degradation-aware prompt adapter to facilitate content-driven conditional diffusion for generating domain-related images. Specifically, a contrast-based degradation prompt adapter is firstly designed to capture degradation-aware prompts from web-collected degraded images. Then, the collected unpaired clean images are perturbed to latent features of stable diffusion, and conditioned with the degradation-aware prompts to synthesize new domain-related degraded images for knowledge distillation. Experiments illustrate that our proposal achieves comparable performance to the model distilled with original training data, and is even superior to other mainstream unsupervised methods. |
|
| Multiple weather images restoration using the task transformer and adaptive mixup strategy | 2024-09-05 | ShowThe current state-of-the-art in severe weather removal predominantly focuses on single-task applications, such as rain removal, haze removal, and snow removal. However, real-world weather conditions often consist of a mixture of several weather types, and the degree of weather mixing in autonomous driving scenarios remains unknown. In the presence of complex and diverse weather conditions, a single weather removal model often encounters challenges in producing clear images from severe weather images. Therefore, there is a need for the development of multi-task severe weather removal models that can effectively handle mixed weather conditions and improve image quality in autonomous driving scenarios. In this paper, we introduce a novel multi-task severe weather removal model that can effectively handle complex weather conditions in an adaptive manner. Our model incorporates a weather task sequence generator, enabling the self-attention mechanism to selectively focus on features specific to different weather types. To tackle the challenge of repairing large areas of weather degradation, we introduce Fast Fourier Convolution (FFC) to increase the receptive field. Additionally, we propose an adaptive upsampling technique that effectively processes both the weather task information and underlying image features by selectively retaining relevant information. Our proposed model has achieved state-of-the-art performance on the publicly available dataset. |
10 pa...10 pages, 5 figures and 2 table |
| Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem | 2024-09-05 | ShowTraining Single-Image Super-Resolution (SISR) models using pixel-based regression losses can achieve high distortion metrics scores (e.g., PSNR and SSIM), but often results in blurry images due to insufficient recovery of high-frequency details. Conversely, using GAN or perceptual losses can produce sharp images with high perceptual metric scores (e.g., LPIPS), but may introduce artifacts and incorrect textures. Balancing these two types of losses can help achieve a trade-off between distortion and perception, but the challenge lies in tuning the loss function weights. To address this issue, we propose a novel method that incorporates Multi-Objective Optimization (MOO) into the training process of SISR models to balance perceptual quality and distortion. We conceptualize the relationship between loss weights and image quality assessment (IQA) metrics as black-box objective functions to be optimized within our Multi-Objective Bayesian Optimization Super-Resolution (MOBOSR) framework. This approach automates the hyperparameter tuning process, reduces overall computational cost, and enables the use of numerous loss functions simultaneously. Extensive experiments demonstrate that MOBOSR outperforms state-of-the-art methods in terms of both perceptual quality and distortion, significantly advancing the perception-distortion Pareto frontier. Our work points towards a new direction for future research on balancing perceptual quality and fidelity in nearly all image restoration tasks. The source code and pretrained models are available at: https://github.com/ZhuKeven/MOBOSR. |
|
| Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models | 2024-09-03 | ShowThis paper addresses the limitations of adverse weather image restoration approaches trained on synthetic data when applied to real-world scenarios. We formulate a semi-supervised learning framework employing vision-language models to enhance restoration performance across diverse adverse weather conditions in real-world settings. Our approach involves assessing image clearness and providing semantics using vision-language models on real data, serving as supervision signals for training restoration models. For clearness enhancement, we use real-world data, utilizing a dual-step strategy with pseudo-labels assessed by vision-language models and weather prompt learning. For semantic enhancement, we integrate real-world data by adjusting weather conditions in vision-language model descriptions while preserving semantic meaning. Additionally, we introduce an effective training strategy to bootstrap restoration performance. Our approach achieves superior results in real-world adverse weather image restoration, demonstrated through qualitative and quantitative comparisons with state-of-the-art works. |
Accep...Accepted by ECCV 2024 |
| F2former: When Fractional Fourier Meets Deep Wiener Deconvolution and Selective Frequency Transformer for Image Deblurring | 2024-09-03 | ShowRecent progress in image deblurring techniques focuses mainly on operating in both frequency and spatial domains using the Fourier transform (FT) properties. However, their performance is limited due to the dependency of FT on stationary signals and its lack of capability to extract spatial-frequency properties. In this paper, we propose a novel approach based on the Fractional Fourier Transform (FRFT), a unified spatial-frequency representation leveraging both spatial and frequency components simultaneously, making it ideal for processing non-stationary signals like images. Specifically, we introduce a Fractional Fourier Transformer (F2former), where we combine the classical fractional Fourier based Wiener deconvolution (F2WD) as well as a multi-branch encoder-decoder transformer based on a new fractional frequency aware transformer block (F2TB). We design F2TB consisting of a fractional frequency aware self-attention (F2SA) to estimate element-wise product attention based on important frequency components and a novel feed-forward network based on frequency division multiplexing (FM-FFN) to refine high and low frequency features separately for efficient latent clear image restoration. Experimental results for the cases of both motion deblurring as well as defocus deblurring show that the performance of our proposed method is superior to other state-of-the-art (SOTA) approaches. |
20 pages, 21 figures |
| Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance | 2024-09-03 | ShowThere are many excellent solutions in image restoration.However, most methods require on training separate models to restore images with different types of degradation.Although existing all-in-one models effectively address multiple types of degradation simultaneously, their performance in real-world scenarios is still constrained by the task confusion problem.In this work, we attempt to address this issue by introducing \textbf{Restorer}, a novel Transformer-based all-in-one image restoration model.To effectively address the complex degradation present in real-world images, we propose All-Axis Attention (AAA), a mechanism that simultaneously models long-range dependencies across both spatial and channel dimensions, capturing potential correlations along all axes.Additionally, we introduce textual prompts in Restorer to incorporate explicit task priors, enabling the removal of specific degradation types based on user instructions. By iterating over these prompts, Restorer can handle composite degradation in real-world scenarios without requiring additional training.Based on these designs, Restorer with one set of parameters demonstrates state-of-the-art performance in multiple image restoration tasks compared to existing all-in-one and even single-task models.Additionally, Restorer is efficient during inference, suggesting the potential in real-world applications. |
|
| GaussianPU: A Hybrid 2D-3D Upsampling Framework for Enhancing Color Point Clouds via 3D Gaussian Splatting | 2024-09-03 | ShowDense colored point clouds enhance visual perception and are of significant value in various robotic applications. However, existing learning-based point cloud upsampling methods are constrained by computational resources and batch processing strategies, which often require subdividing point clouds into smaller patches, leading to distortions that degrade perceptual quality. To address this challenge, we propose a novel 2D-3D hybrid colored point cloud upsampling framework (GaussianPU) based on 3D Gaussian Splatting (3DGS) for robotic perception. This approach leverages 3DGS to bridge 3D point clouds with their 2D rendered images in robot vision systems. A dual scale rendered image restoration network transforms sparse point cloud renderings into dense representations, which are then input into 3DGS along with precise robot camera poses and interpolated sparse point clouds to reconstruct dense 3D point clouds. We have made a series of enhancements to the vanilla 3DGS, enabling precise control over the number of points and significantly boosting the quality of the upsampled point cloud for robotic scene understanding. Our framework supports processing entire point clouds on a single consumer-grade GPU, such as the NVIDIA GeForce RTX 3090, eliminating the need for segmentation and thus producing high-quality, dense colored point clouds with millions of points for robot navigation and manipulation tasks. Extensive experimental results on generating million-level point cloud data validate the effectiveness of our method, substantially improving the quality of colored point clouds and demonstrating significant potential for applications involving large-scale point clouds in autonomous robotics and human-robot interaction scenarios. |
7 pages, 5 figures |
| Accurate Forgetting for All-in-One Image Restoration Model | 2024-09-01 | ShowPrivacy protection has always been an ongoing topic, especially for AI. Currently, a low-cost scheme called Machine Unlearning forgets the private data remembered in the model. Specifically, given a private dataset and a trained neural network, we need to use e.g. pruning, fine-tuning, and gradient ascent to remove the influence of the private dataset on the neural network. Inspired by this, we try to use this concept to bridge the gap between the fields of image restoration and security, creating a new research idea. We propose the scene for the All-In-One model (a neural network that restores a wide range of degraded information), where a given dataset such as haze, or rain, is private and needs to be eliminated from the influence of it on the trained model. Notably, we find great challenges in this task to remove the influence of sensitive data while ensuring that the overall model performance remains robust, which is akin to directing a symphony orchestra without specific instruments while keeping the playing soothing. Here we explore a simple but effective approach: Instance-wise Unlearning through the use of adversarial examples and gradient ascent techniques. Our approach is a low-cost solution compared to the strategy of retraining the model from scratch, where the gradient ascent trick forgets the specified data and the performance of the adversarial sample maintenance model is robust. Through extensive experimentation on two popular unified image restoration models, we show that our approach effectively preserves knowledge of remaining data while unlearning a given degradation type. |
|
| AWRaCLe: All-Weather Image Restoration using Visual In-Context Learning | 2024-08-30 | ShowAll-Weather Image Restoration (AWIR) under adverse weather conditions is a challenging task due to the presence of different types of degradations. Prior research in this domain relies on extensive training data but lacks the utilization of additional contextual information for restoration guidance. Consequently, the performance of existing methods is limited by the degradation cues that are learnt from individual training samples. Recent advancements in visual in-context learning have introduced generalist models that are capable of addressing multiple computer vision tasks simultaneously by using the information present in the provided context as a prior. In this paper, we propose All-Weather Image Restoration using Visual In-Context Learning (AWRaCLe), a novel approach for AWIR that innovatively utilizes degradation-specific visual context information to steer the image restoration process. To achieve this, AWRaCLe incorporates Degradation Context Extraction (DCE) and Context Fusion (CF) to seamlessly integrate degradation-specific features from the context into an image restoration network. The proposed DCE and CF blocks leverage CLIP features and incorporate attention mechanisms to adeptly learn and fuse contextual information. These blocks are specifically designed for visual in-context learning under all-weather conditions and are crucial for effective context utilization. Through extensive experiments, we demonstrate the effectiveness of AWRaCLe for all-weather restoration and show that our method advances the state-of-the-art in AWIR. |
|
| Efficient Image Restoration through Low-Rank Adaptation and Stable Diffusion XL | 2024-08-30 | ShowIn this study, we propose an enhanced image restoration model, SUPIR, based on the integration of two low-rank adaptive (LoRA) modules with the Stable Diffusion XL (SDXL) framework. Our method leverages the advantages of LoRA to fine-tune SDXL models, thereby significantly improving image restoration quality and efficiency. We collect 2600 high-quality real-world images, each with detailed descriptive text, for training the model. The proposed method is evaluated on standard benchmarks and achieves excellent performance, demonstrated by higher peak signal-to-noise ratio (PSNR), lower learned perceptual image patch similarity (LPIPS), and higher structural similarity index measurement (SSIM) scores. These results underscore the effectiveness of combining LoRA with SDXL for advanced image restoration tasks, highlighting the potential of our approach in generating high-fidelity restored images. |
10 pages |
| GameIR: A Large-Scale Synthesized Ground-Truth Dataset for Image Restoration over Gaming Content | 2024-08-29 | ShowImage restoration methods like super-resolution and image synthesis have been successfully used in commercial cloud gaming products like NVIDIA's DLSS. However, restoration over gaming content is not well studied by the general public. The discrepancy is mainly caused by the lack of ground-truth gaming training data that match the test cases. Due to the unique characteristics of gaming content, the common approach of generating pseudo training data by degrading the original HR images results in inferior restoration performance. In this work, we develop GameIR, a large-scale high-quality computer-synthesized ground-truth dataset to fill in the blanks, targeting at two different applications. The first is super-resolution with deferred rendering, to support the gaming solution of rendering and transferring LR images only and restoring HR images on the client side. We provide 19200 LR-HR paired ground-truth frames coming from 640 videos rendered at 720p and 1440p for this task. The second is novel view synthesis (NVS), to support the multiview gaming solution of rendering and transferring part of the multiview frames and generating the remaining frames on the client side. This task has 57,600 HR frames from 960 videos of 160 scenes with 6 camera views. In addition to the RGB frames, the GBuffers during the deferred rendering stage are also provided, which can be used to help restoration. Furthermore, we evaluate several SOTA super-resolution algorithms and NeRF-based NVS algorithms over our dataset, which demonstrates the effectiveness of our ground-truth GameIR data in improving restoration performance for gaming content. Also, we test the method of incorporating the GBuffers as additional input information for helping super-resolution and NVS. We release our dataset and models to the general public to facilitate research on restoration methods over gaming content. |
|
| Enhanced Control for Diffusion Bridge in Image Restoration | 2024-08-29 | ShowImage restoration refers to the process of restoring a damaged low-quality image back to its corresponding high-quality image. Typically, we use convolutional neural networks to directly learn the mapping from low-quality images to high-quality images achieving image restoration. Recently, a special type of diffusion bridge model has achieved more advanced results in image restoration. It can transform the direct mapping from low-quality to high-quality images into a diffusion process, restoring low-quality images through a reverse process. However, the current diffusion bridge restoration models do not emphasize the idea of conditional control, which may affect performance. This paper introduces the ECDB model enhancing the control of the diffusion bridge with low-quality images as conditions. Moreover, in response to the characteristic of diffusion models having low denoising level at larger values of (\bm t ), we also propose a Conditional Fusion Schedule, which more effectively handles the conditional feature information of various modules. Experimental results prove that the ECDB model has achieved state-of-the-art results in many image restoration tasks, including deraining, inpainting and super-resolution. Code is avaliable at https://github.com/Hammour-steak/ECDB. |
|
| Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration | 2024-08-28 | ShowThe limitations of task-specific and general image restoration methods for specific degradation have prompted the development of all-in-one image restoration techniques. However, the diversity of patterns among multiple degradation, along with the significant uncertainties in mapping between degraded images of different severities and their corresponding undistorted versions, pose significant challenges to the all-in-one restoration tasks. To address these challenges, we propose Perceive-IR, an all-in-one image restorer designed to achieve fine-grained quality control that enables restored images to more closely resemble their undistorted counterparts, regardless of the type or severity of degradation. Specifically, Perceive-IR contains two stages: (1) prompt learning stage and (2) restoration stage. In the prompt learning stage, we leverage prompt learning to acquire a fine-grained quality perceiver capable of distinguishing three-tier quality levels by constraining the prompt-image similarity in the CLIP perception space. Subsequently, this quality perceiver and difficulty-adaptive perceptual loss are integrated as a quality-aware learning strategy to realize fine-grained quality control in restoration stage. For the restoration stage, a semantic guidance module (SGM) and compact feature extraction (CFE) are proposed to further promote the restoration process by utilizing the robust semantic information from the pre-trained large scale vision models and distinguishing degradation-specific features. Extensive experiments demonstrate that our Perceive-IR outperforms state-of-the-art methods in all-in-one image restoration tasks and exhibit superior generalization ability when dealing with unseen tasks. |
13 pages, 8 figures |
| HAIR: Hypernetworks-based All-in-One Image Restoration | 2024-08-28 | ShowImage restoration aims to recover a high-quality clean image from its degraded version. Recent progress in image restoration has demonstrated the effectiveness of All-in-One image restoration models in addressing various degradations simultaneously. However, these existing methods typically utilize the same parameters to tackle images with different degradation types, thus forcing the model to balance the performance between different tasks and limiting its performance on each task. To alleviate this issue, we propose HAIR, a \textbf{H}ypernetworks-based \textbf{A}ll-in-One \textbf{I}mage \textbf{R}estoration method that dynamically generates parameters based on input images. Specifically, HAIR consists of two main components, i.e., Classifier and Hyper Selecting Net (HSN). The Classifier is a simple image classification network used to generate a Global Information Vector (GIV) that contains the degradation information of the input image, and the HSN is a simple fully-connected neural network that receives the GIV and outputs parameters for the corresponding modules. Extensive experiments demonstrate that HAIR can significantly improve the performance of existing image restoration models in a plug-and-play manner, both in single-task and all-in-one settings. Notably, our innovative model, Res-HAIR, which integrates HAIR into the well-known Restormer, can obtain superior or comparable performance compared with current state-of-the-art methods. Moreover, we theoretically demonstrate that our proposed HAIR requires fewer parameters in contrast to the prevalent All-in-One methodologies. The code is available at \textcolor{blue}{\href{https://github.com/toummHus/HAIR}{https://github.com/toummHus/HAIR}.} |
16 pages |
| Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models | 2024-08-28 | ShowCross-view geo-localization in GNSS-denied environments aims to determine an unknown location by matching drone-view images with the correct geo-tagged satellite-view images from a large gallery. Recent research shows that learning discriminative image representations under specific weather conditions can significantly enhance performance. However, the frequent occurrence of unseen extreme weather conditions hinders progress. This paper introduces MCGF, a Multi-weather Cross-view Geo-localization Framework designed to dynamically adapt to unseen weather conditions. MCGF establishes a joint optimization between image restoration and geo-localization using denoising diffusion models. For image restoration, MCGF incorporates a shared encoder and a lightweight restoration module to help the backbone eliminate weather-specific information. For geo-localization, MCGF uses EVA-02 as a backbone for feature extraction, with cross-entropy loss for training and cosine distance for testing. Extensive experiments on University160k-WX demonstrate that MCGF achieves competitive results for geo-localization in varying weather conditions. |
Accep...Accepted by ACM MM24 workshop |
| A Preliminary Exploration Towards General Image Restoration | 2024-08-27 | ShowDespite the tremendous success of deep models in various individual image restoration tasks, there are at least two major technical challenges preventing these works from being applied to real-world usages: (1) the lack of generalization ability and (2) the complex and unknown degradations in real-world scenarios. Existing deep models, tailored for specific individual image restoration tasks, often fall short in effectively addressing these challenges. In this paper, we present a new problem called general image restoration (GIR) which aims to address these challenges within a unified model. GIR covers most individual image restoration tasks (\eg, image denoising, deblurring, deraining and super-resolution) and their combinations for general purposes. This paper proceeds to delineate the essential aspects of GIR, including problem definition and the overarching significance of generalization performance. Moreover, the establishment of new datasets and a thorough evaluation framework for GIR models is discussed. We conduct a comprehensive evaluation of existing approaches for tackling the GIR challenge, illuminating their strengths and pragmatic challenges. By analyzing these approaches, we not only underscore the effectiveness of GIR but also highlight the difficulties in its practical implementation. At last, we also try to understand and interpret these models' behaviors to inspire the future direction. Our work can open up new valuable research directions and contribute to the research of general vision. |
|
| CODE: Confident Ordinary Differential Editing | 2024-08-22 | ShowConditioning image generation facilitates seamless editing and the creation of photorealistic images. However, conditioning on noisy or Out-of-Distribution (OoD) images poses significant challenges, particularly in balancing fidelity to the input and realism of the output. We introduce Confident Ordinary Differential Editing (CODE), a novel approach for image synthesis that effectively handles OoD guidance images. Utilizing a diffusion model as a generative prior, CODE enhances images through score-based updates along the probability-flow Ordinary Differential Equation (ODE) trajectory. This method requires no task-specific training, no handcrafted modules, and no assumptions regarding the corruptions affecting the conditioning image. Our method is compatible with any diffusion model. Positioned at the intersection of conditional image generation and blind image restoration, CODE operates in a fully blind manner, relying solely on a pre-trained generative model. Our method introduces an alternative approach to blind restoration: instead of targeting a specific ground truth image based on assumptions about the underlying corruption, CODE aims to increase the likelihood of the input image while maintaining fidelity. This results in the most probable in-distribution image around the input. Our contributions are twofold. First, CODE introduces a novel editing method based on ODE, providing enhanced control, realism, and fidelity compared to its SDE-based counterpart. Second, we introduce a confidence interval-based clipping method, which improves CODE's effectiveness by allowing it to disregard certain pixels or information, thus enhancing the restoration process in a blind manner. Experimental results demonstrate CODE's effectiveness over existing methods, particularly in scenarios involving severe degradation or OoD inputs. |
|
| Unfolded proximal neural networks for robust image Gaussian denoising | 2024-08-21 | ShowA common approach to solve inverse imaging problems relies on finding a maximum a posteriori (MAP) estimate of the original unknown image, by solving a minimization problem. In thiscontext, iterative proximal algorithms are widely used, enabling to handle non-smooth functions and linear operators. Recently, these algorithms have been paired with deep learning strategies, to further improve the estimate quality. In particular, proximal neural networks (PNNs) have been introduced, obtained by unrolling a proximal algorithm as for finding a MAP estimate, but over a fixed number of iterations, with learned linear operators and parameters. As PNNs are based on optimization theory, they are very flexible, and can be adapted to any image restoration task, as soon as a proximal algorithm can solve it. They further have much lighter architectures than traditional networks. In this article we propose a unified framework to build PNNs for the Gaussian denoising task, based on both the dual-FB and the primal-dual Chambolle-Pock algorithms. We further show that accelerated inertial versions of these algorithms enable skip connections in the associated NN layers. We propose different learning strategies for our PNN framework, and investigate their robustness (Lipschitz property) and denoising efficiency. Finally, we assess the robustness of our PNNs when plugged in a forward-backward algorithm for an image deblurring problem. |
|
| OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal | 2024-08-21 | ShowDeep learning-based methods have shown remarkable performance in single JPEG artifacts removal task. However, existing methods tend to degrade on double JPEG images, which are prevalent in real-world scenarios. To address this issue, we propose Offset-Aware Partition Transformer for double JPEG artifacts removal, termed as OAPT. We conduct an analysis of double JPEG compression that results in up to four patterns within each 8x8 block and design our model to cluster the similar patterns to remedy the difficulty of restoration. Our OAPT consists of two components: compression offset predictor and image reconstructor. Specifically, the predictor estimates pixel offsets between the first and second compression, which are then utilized to divide different patterns. The reconstructor is mainly based on several Hybrid Partition Attention Blocks (HPAB), combining vanilla window-based self-attention and sparse attention for clustered pattern features. Extensive experiments demonstrate that OAPT outperforms the state-of-the-art method by more than 0.16dB in double JPEG image restoration task. Moreover, without increasing any computation cost, the pattern clustering module in HPAB can serve as a plugin to enhance other transformer-based image restoration methods. The code will be available at https://github.com/QMoQ/OAPT.git . |
14 pa...14 pages, 9 figures. Codes and models are available at https://github.com/QMoQ/OAPT.git |
| Taming Generative Diffusion for Universal Blind Image Restoration | 2024-08-21 | ShowDiffusion models have been widely utilized for image restoration. However, previous blind image restoration methods still need to assume the type of degradation model while leaving the parameters to be optimized, limiting their real-world applications. Therefore, we aim to tame generative diffusion prior for universal blind image restoration dubbed BIR-D, which utilizes an optimizable convolutional kernel to simulate the degradation model and dynamically update the parameters of the kernel in the diffusion steps, enabling it to achieve blind image restoration results even in various complex situations. Besides, based on mathematical reasoning, we have provided an empirical formula for the chosen of adaptive guidance scale, eliminating the need for a grid search for the optimal parameter. Experimentally, Our BIR-D has demonstrated superior practicality and versatility than off-the-shelf unsupervised methods across various tasks both on real-world and synthetic datasets, qualitatively and quantitatively. BIR-D is able to fulfill multi-guidance blind image restoration. Moreover, BIR-D can also restore images that undergo multiple and complicated degradations, demonstrating the practical applications. |
14 pa...14 pages, 9 figures, 8 tables |
| DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency | 2024-08-19 | ShowDiffusion models have established new state of the art in a multitude of computer vision tasks, including image restoration. Diffusion-based inverse problem solvers generate reconstructions of exceptional visual quality from heavily corrupted measurements. However, in what is widely known as the perception-distortion trade-off, the price of perceptually appealing reconstructions is often paid in declined distortion metrics, such as PSNR. Distortion metrics measure faithfulness to the observation, a crucial requirement in inverse problems. In this work, we propose a novel framework for inverse problem solving, namely we assume that the observation comes from a stochastic degradation process that gradually degrades and noises the original clean image. We learn to reverse the degradation process in order to recover the clean image. Our technique maintains consistency with the original measurement throughout the reverse process, and allows for great flexibility in trading off perceptual quality for improved distortion metrics and sampling speedup via early-stopping. We demonstrate the efficiency of our method on different high-resolution datasets and inverse problems, achieving great improvements over other state-of-the-art diffusion-based methods with respect to both perceptual and distortion metrics. |
30 pa...30 pages, 15 figures, published at the 41st International Conference on Machine Learning, Vienna, Austria, 2024 |
| Multi-Scale Representation Learning for Image Restoration with State-Space Model | 2024-08-19 | ShowImage restoration endeavors to reconstruct a high-quality, detail-rich image from a degraded counterpart, which is a pivotal process in photography and various computer vision systems. In real-world scenarios, different types of degradation can cause the loss of image details at various scales and degrade image contrast. Existing methods predominantly rely on CNN and Transformer to capture multi-scale representations. However, these methods are often limited by the high computational complexity of Transformers and the constrained receptive field of CNN, which hinder them from achieving superior performance and efficiency in image restoration. To address these challenges, we propose a novel Multi-Scale State-Space Model-based (MS-Mamba) for efficient image restoration that enhances the capacity for multi-scale representation learning through our proposed global and regional SSM modules. Additionally, an Adaptive Gradient Block (AGB) and a Residual Fourier Block (RFB) are proposed to improve the network's detail extraction capabilities by capturing gradients in various directions and facilitating learning details in the frequency domain. Extensive experiments on nine public benchmarks across four classic image restoration tasks, image deraining, dehazing, denoising, and low-light enhancement, demonstrate that our proposed method achieves new state-of-the-art performance while maintaining low computational complexity. The source code will be publicly available. |
|
| Harnessing Multi-resolution and Multi-scale Attention for Underwater Image Restoration | 2024-08-19 | ShowUnderwater imagery is often compromised by factors such as color distortion and low contrast, posing challenges for high-level vision tasks. Recent underwater image restoration (UIR) methods either analyze the input image at full resolution, resulting in spatial richness but contextual weakness, or progressively from high to low resolution, yielding reliable semantic information but reduced spatial accuracy. Here, we propose a lightweight multi-stage network called Lit-Net that focuses on multi-resolution and multi-scale image analysis for restoring underwater images while retaining original resolution during the first stage, refining features in the second, and focusing on reconstruction in the final stage. Our novel encoder block utilizes parallel |
|
| Re-boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image Restoration | 2024-08-17 | ShowUnsupervised restoration approaches based on generative adversarial networks (GANs) offer a promising solution without requiring paired datasets. Yet, these GAN-based approaches struggle to surpass the performance of conventional unsupervised GAN-based frameworks without significantly modifying model structures or increasing the computational complexity. To address these issues, we propose a self-collaboration (SC) strategy for existing restoration models. This strategy utilizes information from the previous stage as feedback to guide subsequent stages, achieving significant performance improvement without increasing the framework's inference complexity. The SC strategy comprises a prompt learning (PL) module and a restorer ( |
This ...This paper is an extended and revised version of our previous work "Unsupervised Image Denoising in Real-World Scenarios via Self-Collaboration Parallel Generative Adversarial Branches"(https://openaccess.thecvf.com/content/ICCV2023/papers/Lin_Unsupervised_Image_Denoising_in_Real-World_Scenarios_via_Self-Collaboration_Parallel_Generative_ICCV_2023_paper.pdf) |
| Multi-task Image Restoration Guided By Robust DINO Features | 2024-08-16 | ShowMulti-task image restoration has gained significant interest due to its inherent versatility and efficiency compared to its single-task counterpart. However, performance decline is observed with an increase in the number of tasks, primarily attributed to the restoration model's challenge in handling different tasks with distinct natures at the same time. Thus, a perspective emerged aiming to explore the degradation-insensitive semantic commonalities among different degradation tasks. In this paper, we observe that the features of DINOv2 can effectively model semantic information and are independent of degradation factors. Motivated by this observation, we propose \mbox{\textbf{DINO-IR}}, a multi-task image restoration approach leveraging robust features extracted from DINOv2 to solve multi-task image restoration simultaneously. We first propose a pixel-semantic fusion (PSF) module to dynamically fuse DINOV2's shallow features containing pixel-level information and deep features containing degradation-independent semantic information. To guide the restoration model with the features of DINOv2, we develop a DINO-Restore adaption and fusion module to adjust the channel of fused features from PSF and then integrate them with the features from the restoration model. By formulating these modules into a unified deep model, we propose a DINO perception contrastive loss to constrain the model training. Extensive experimental results demonstrate that our DINO-IR performs favorably against existing multi-task image restoration approaches in various tasks by a large margin. The source codes and trained models will be made available. |
|
| Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks | 2024-08-15 | ShowRecent research tries to extend image restoration capabilities from human perception to machine perception, thereby enhancing the performance of high-level vision tasks in degraded environments. These methods, primarily based on supervised learning, typically involve the retraining of restoration networks or high-level vision networks. However, collecting paired data in real-world scenarios and retraining large-scale models are challenge. To this end, we propose an unsupervised learning method called \textbf{Va}riational \textbf{T}ranslator (VaT), which does not require retraining existing restoration and high-level vision networks. Instead, it establishes a lightweight network that serves as an intermediate bridge between them. By variational inference, VaT approximates the joint distribution of restoration output and high-level vision input, dividing the optimization objective into preserving content and maximizing marginal likelihood associated with high-level vision tasks. By cleverly leveraging self-training paradigms, VaT achieves the above optimization objective without requiring labels. As a result, the translated images maintain a close resemblance to their original content while also demonstrating exceptional performance on high-level vision tasks. Extensive experiments in dehazing and low-light enhancement for detection and classification show the superiority of our method over other state-of-the-art unsupervised counterparts, even significantly surpassing supervised methods in some complex real-world scenarios. |
|
| Review Learning: Advancing All-in-One Ultra-High-Definition Image Restoration Training Method | 2024-08-13 | ShowAll-in-one image restoration tasks are becoming increasingly important, especially for ultra-high-definition (UHD) images. Existing all-in-one UHD image restoration methods usually boost the model's performance by introducing prompt or customized dynamized networks for different degradation types. For the inference stage, it might be friendly, but in the training stage, since the model encounters multiple degraded images of different quality in an epoch, these cluttered learning objectives might be information pollution for the model. To address this problem, we propose a new training paradigm for general image restoration models, which we name \textbf{Review Learning}, which enables image restoration models to be capable enough to handle multiple types of degradation without prior knowledge and prompts. This approach begins with sequential training of an image restoration model on several degraded datasets, combined with a review mechanism that enhances the image restoration model's memory for several previous classes of degraded datasets. In addition, we design a lightweight all-purpose image restoration network that can efficiently reason about degraded images with 4K ( |
|
| Wavelet based inpainting detection | 2024-08-12 | ShowWith the advancement in image editing tools, manipulating digital images has become alarmingly easy. Inpainting, which is used to remove objects or fill in parts of an image, serves as a powerful tool for both image restoration and forgery. This paper introduces a novel approach for detecting image inpainting forgeries by combining DT-CWT with Hierarchical Feature segmentation and with noise inconsistency analysis. The DT-CWT offers several advantages for this task, including inherent shift-invariance, which makes it robust to minor manipulations during the inpainting process, and directional selectivity, which helps capture subtle artifacts introduced by inpainting in specific frequency bands and orientations. By first applying color image segmentation and then analyzing for each segment, noise inconsistency obtained via DT-CW we can identify patterns indicative of inpainting forgeries. The proposed method is evaluated on a benchmark dataset created for this purpose and is compared with existing forgery detection techniques. Our approach demonstrates superior results compared with SOTA in detecting inpainted images. |
|
| Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration | 2024-08-12 | ShowWe propose an image restoration algorithm that can control the perceptual quality and/or the mean square error (MSE) of any pre-trained model, trading one over the other at test time. Our algorithm is few-shot: Given about a dozen images restored by the model, it can significantly improve the perceptual quality and/or the MSE of the model for newly restored images without further training. Our approach is motivated by a recent theoretical result that links between the minimum MSE (MMSE) predictor and the predictor that minimizes the MSE under a perfect perceptual quality constraint. Specifically, it has been shown that the latter can be obtained by optimally transporting the output of the former, such that its distribution matches the source data. Thus, to improve the perceptual quality of a predictor that was originally trained to minimize MSE, we approximate the optimal transport by a linear transformation in the latent space of a variational auto-encoder, which we compute in closed-form using empirical means and covariances. Going beyond the theory, we find that applying the same procedure on models that were initially trained to achieve high perceptual quality, typically improves their perceptual quality even further. And by interpolating the results with the original output of the model, we can improve their MSE on the expense of perceptual quality. We illustrate our method on a variety of degradations applied to general content images of arbitrary dimensions. |
|
| Greedy randomized block Kaczmarz method for matrix equation AXB=C and its applications in color image restoration | 2024-08-10 | ShowIn view of the advantages of simplicity and effectiveness of the Kaczmarz method, which was originally employed to solve the large-scale system of linear equations |
|
| Physical prior guided cooperative learning framework for joint turbulence degradation estimation and infrared video restoration | 2024-08-08 | ShowInfrared imaging and turbulence strength measurements are in widespread demand in many fields. This paper introduces a Physical Prior Guided Cooperative Learning (P2GCL) framework to jointly enhance atmospheric turbulence strength estimation and infrared image restoration. P2GCL involves a cyclic collaboration between two models, i.e., a TMNet measures turbulence strength and outputs the refractive index structure constant (Cn2) as a physical prior, a TRNet conducts infrared image sequence restoration based on Cn2 and feeds the restored images back to the TMNet to boost the measurement accuracy. A novel Cn2-guided frequency loss function and a physical constraint loss are introduced to align the training process with physical theories. Experiments demonstrate P2GCL achieves the best performance for both turbulence strength estimation (improving Cn2 MAE by 0.0156, enhancing R2 by 0.1065) and image restoration (enhancing PSNR by 0.2775 dB), validating the significant impact of physical prior guided cooperative learning. |
21 |
| MultiColor: Image Colorization by Learning from Multiple Color Spaces | 2024-08-08 | ShowDeep networks have shown impressive performance in the image restoration tasks, such as image colorization. However, we find that previous approaches rely on the digital representation from single color model with a specific mapping function, a.k.a., color space, during the colorization pipeline. In this paper, we first investigate the modeling of different color spaces, and find each of them exhibiting distinctive characteristics with unique distribution of colors. The complementarity among multiple color spaces leads to benefits for the image colorization task. We present MultiColor, a new learning-based approach to automatically colorize grayscale images that combines clues from multiple color spaces. Specifically, we employ a set of dedicated colorization modules for individual color space. Within each module, a transformer decoder is first employed to refine color query embeddings and then a color mapper produces color channel prediction using the embeddings and semantic features. With these predicted color channels representing various color spaces, a complementary network is designed to exploit the complementarity and generate pleasing and reasonable colorized images. We conduct extensive experiments on real-world datasets, and the results demonstrate superior performance over the state-of-the-arts. |
|
| Diffusion Posterior Proximal Sampling for Image Restoration | 2024-08-06 | ShowDiffusion models have demonstrated remarkable efficacy in generating high-quality samples. Existing diffusion-based image restoration algorithms exploit pre-trained diffusion models to leverage data priors, yet they still preserve elements inherited from the unconditional generation paradigm. These strategies initiate the denoising process with pure white noise and incorporate random noise at each generative step, leading to over-smoothed results. In this paper, we present a refined paradigm for diffusion-based image restoration. Specifically, we opt for a sample consistent with the measurement identity at each generative step, exploiting the sampling selection as an avenue for output stability and enhancement. The number of candidate samples used for selection is adaptively determined based on the signal-to-noise ratio of the timestep. Additionally, we start the restoration process with an initialization combined with the measurement signal, providing supplementary information to better align the generative process. Extensive experimental results and analyses validate that our proposed method significantly enhances image restoration performance while consuming negligible additional computational resources. |
ACM M...ACM Multimedia 2024 Oral |
| Holistic Dynamic Frequency Transformer for Image Fusion and Exposure Correction | 2024-08-03 | ShowThe correction of exposure-related issues is a pivotal component in enhancing the quality of images, offering substantial implications for various computer vision tasks. Historically, most methodologies have predominantly utilized spatial domain recovery, offering limited consideration to the potentialities of the frequency domain. Additionally, there has been a lack of a unified perspective towards low-light enhancement, exposure correction, and multi-exposure fusion, complicating and impeding the optimization of image processing. In response to these challenges, this paper proposes a novel methodology that leverages the frequency domain to improve and unify the handling of exposure correction tasks. Our method introduces Holistic Frequency Attention and Dynamic Frequency Feed-Forward Network, which replace conventional correlation computation in the spatial-domain. They form a foundational building block that facilitates a U-shaped Holistic Dynamic Frequency Transformer as a filter to extract global information and dynamically select important frequency bands for image restoration. Complementing this, we employ a Laplacian pyramid to decompose images into distinct frequency bands, followed by multiple restorers, each tuned to recover specific frequency-band information. The pyramid fusion allows a more detailed and nuanced image restoration process. Ultimately, our structure unifies the three tasks of low-light enhancement, exposure correction, and multi-exposure fusion, enabling comprehensive treatment of all classical exposure errors. Benchmarking on mainstream datasets for these tasks, our proposed method achieves state-of-the-art results, paving the way for more sophisticated and unified solutions in exposure correction. |
|
| Contribution-based Low-Rank Adaptation with Pre-training Model for Real Image Restoration | 2024-08-02 | ShowRecently, pre-trained model and efficient parameter tuning have achieved remarkable success in natural language processing and high-level computer vision with the aid of masked modeling and prompt tuning. In low-level computer vision, however, there have been limited investigations on pre-trained models and even efficient fine-tuning strategy has not yet been explored despite its importance and benefit in various real-world tasks such as alleviating memory inflation issue when integrating new tasks on AI edge devices. Here, we propose a novel efficient parameter tuning approach dubbed contribution-based low-rank adaptation (CoLoRA) for multiple image restorations along with effective pre-training method with random order degradations (PROD). Unlike prior arts that tune all network parameters, our CoLoRA effectively fine-tunes small amount of parameters by leveraging LoRA (low-rank adaptation) for each new vision task with our contribution-based method to adaptively determine layer by layer capacity for that task to yield comparable performance to full tuning. Furthermore, our PROD strategy allows to extend the capability of pre-trained models with improved performance as well as robustness to bridge synthetic pre-training and real-world fine-tuning. Our CoLoRA with PROD has demonstrated its superior performance in various image restoration tasks across diverse degradation types on both synthetic and real-world datasets for known and novel tasks. |
33 pa...33 pages, 15 figures, for homepage see this url : https://janeyeon.github.io/colora/ |
| Osmosis: RGBD Diffusion Prior for Underwater Image Restoration | 2024-08-01 | ShowUnderwater image restoration is a challenging task because of water effects that increase dramatically with distance. This is worsened by lack of ground truth data of clean scenes without water. Diffusion priors have emerged as strong image restoration priors. However, they are often trained with a dataset of the desired restored output, which is not available in our case. We also observe that using only color data is insufficient, and therefore augment the prior with a depth channel. We train an unconditional diffusion model prior on the joint space of color and depth, using standard RGBD datasets of natural outdoor scenes in air. Using this prior together with a novel guidance method based on the underwater image formation model, we generate posterior samples of clean images, removing the water effects. Even though our prior did not see any underwater images during training, our method outperforms state-of-the-art baselines for image restoration on very challenging scenes. Our code, models and data are available on the project website. |
ECCV ...ECCV 2024. Project page with results and code: https://osmosis-diffusion.github.io/ |
| A Prior Embedding-Driven Architecture for Long Distance Blind Iris Recognition | 2024-08-01 | ShowBlind iris images, which result from unknown degradation during the process of iris recognition at long distances, often lead to decreased iris recognition rates. Currently, little existing literature offers a solution to this problem. In response, we propose a prior embedding-driven architecture for long distance blind iris recognition. We first proposed a blind iris image restoration network called Iris-PPRGAN. To effectively restore the texture of the blind iris, Iris-PPRGAN includes a Generative Adversarial Network (GAN) used as a Prior Decoder, and a DNN used as the encoder. To extract iris features more efficiently, we then proposed a robust iris classifier by modifying the bottleneck module of InsightFace, which called Insight-Iris. A low-quality blind iris image is first restored by Iris-PPRGAN, then the restored iris image undergoes recognition via Insight-Iris. Experimental results on the public CASIA-Iris-distance dataset demonstrate that our proposed method significantly superior results to state-of-the-art blind iris restoration methods both quantitatively and qualitatively, Specifically, the recognition rate for long-distance blind iris images reaches 90% after processing with our methods, representing an improvement of approximately ten percentage points compared to images without restoration. |
|
| Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV | 2024-07-31 | ShowTransformers have revolutionized medical image restoration, but the quadratic complexity still poses limitations for their application to high-resolution medical images. The recent advent of RWKV in the NLP field has attracted much attention as it can process long sequences efficiently. To leverage its advanced design, we propose Restore-RWKV, the first RWKV-based model for medical image restoration. Since the original RWKV model is designed for 1D sequences, we make two necessary modifications for modeling spatial relations in 2D images. First, we present a recurrent WKV (Re-WKV) attention mechanism that captures global dependencies with linear computational complexity. Re-WKV incorporates bidirectional attention as basic for a global receptive field and recurrent attention to effectively model 2D dependencies from various scan directions. Second, we develop an omnidirectional token shift (Omni-Shift) layer that enhances local dependencies by shifting tokens from all directions and across a wide context range. These adaptations make the proposed Restore-RWKV an efficient and effective model for medical image restoration. Extensive experiments demonstrate that Restore-RWKV achieves superior performance across various medical image restoration tasks, including MRI image super-resolution, CT image denoising, PET image synthesis, and all-in-one medical image restoration. Code is available at: \href{https://github.com/Yaziwel/Restore-RWKV.git}{https://github.com/Yaziwel/Restore-RWKV}. |
This ...This paper introduces the first RWKV-based model for image restoration |
| UniProcessor: A Text-induced Unified Low-level Image Processor | 2024-07-30 | ShowImage processing, including image restoration, image enhancement, etc., involves generating a high-quality clean image from a degraded input. Deep learning-based methods have shown superior performance for various image processing tasks in terms of single-task conditions. However, they require to train separate models for different degradations and levels, which limits the generalization abilities of these models and restricts their applications in real-world. In this paper, we propose a text-induced unified image processor for low-level vision tasks, termed UniProcessor, which can effectively process various degradation types and levels, and support multimodal control. Specifically, our UniProcessor encodes degradation-specific information with the subject prompt and process degradations with the manipulation prompt. These context control features are injected into the UniProcessor backbone via cross-attention to control the processing procedure. For automatic subject-prompt generation, we further build a vision-language model for general-purpose low-level degradation perception via instruction tuning techniques. Our UniProcessor covers 30 degradation types, and extensive experiments demonstrate that our UniProcessor can well process these degradations without additional training or tuning and outperforms other competing methods. Moreover, with the help of degradation-aware context control, our UniProcessor first shows the ability to individually handle a single distortion in an image with multiple degradations. |
|
| Inverse Problems with Diffusion Models: A MAP Estimation Perspective | 2024-07-27 | ShowInverse problems have many applications in science and engineering. In Computer vision, several image restoration tasks such as inpainting, deblurring, and super-resolution can be formally modeled as inverse problems. Recently, methods have been developed for solving inverse problems that only leverage a pre-trained unconditional diffusion model and do not require additional task-specific training. In such methods, however, the inherent intractability of determining the conditional score function during the reverse diffusion process poses a real challenge, leaving the methods to settle with an approximation instead, which affects their performance in practice. Here, we propose a MAP estimation framework to model the reverse conditional generation process of a continuous time diffusion model as an optimization process of the underlying MAP objective, whose gradient term is tractable. In theory, the proposed framework can be applied to solve general inverse problems using gradient-based optimization methods. However, given the highly non-convex nature of the loss objective, finding a perfect gradient-based optimization algorithm can be quite challenging, nevertheless, our framework offers several potential research directions. We use our proposed formulation and develop empirically effective algorithms for solving noiseless and noisy image inpainting tasks. We validate our proposed algorithms with extensive experiments across diverse mask settings. |
10 pages |
| Multi-Expert Adaptive Selection: Task-Balancing for All-in-One Image Restoration | 2024-07-27 | ShowThe use of a single image restoration framework to achieve multi-task image restoration has garnered significant attention from researchers. However, several practical challenges remain, including meeting the specific and simultaneous demands of different tasks, balancing relationships between tasks, and effectively utilizing task correlations in model design. To address these challenges, this paper explores a multi-expert adaptive selection mechanism. We begin by designing a feature representation method that accounts for both the pixel channel level and the global level, encompassing low-frequency and high-frequency components of the image. Based on this method, we construct a multi-expert selection and ensemble scheme. This scheme adaptively selects the most suitable expert from the expert library according to the content of the input image and the prompts of the current task. It not only meets the individualized needs of different tasks but also achieves balance and optimization across tasks. By sharing experts, our design promotes interconnections between different tasks, thereby enhancing overall performance and resource utilization. Additionally, the multi-expert mechanism effectively eliminates irrelevant experts, reducing interference from them and further improving the effectiveness and accuracy of image restoration. Experimental results demonstrate that our proposed method is both effective and superior to existing approaches, highlighting its potential for practical applications in multi-task image restoration. |
|
| Dilated Strip Attention Network for Image Restoration | 2024-07-26 | ShowImage restoration is a long-standing task that seeks to recover the latent sharp image from its deteriorated counterpart. Due to the robust capacity of self-attention to capture long-range dependencies, transformer-based methods or some attention-based convolutional neural networks have demonstrated promising results on many image restoration tasks in recent years. However, existing attention modules encounters limited receptive fields or abundant parameters. In order to integrate contextual information more effectively and efficiently, in this paper, we propose a dilated strip attention network (DSAN) for image restoration. Specifically, to gather more contextual information for each pixel from its neighboring pixels in the same row or column, a dilated strip attention (DSA) mechanism is elaborately proposed. By employing the DSA operation horizontally and vertically, each location can harvest the contextual information from a much wider region. In addition, we utilize multi-scale receptive fields across different feature groups in DSA to improve representation learning. Extensive experiments show that our DSAN outperforms state-of-the-art algorithms on several image restoration tasks. |
|
| RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models | 2024-07-25 | ShowNatural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual selection of specific tasks, algorithms, and execution sequences, which is time-consuming and may yield suboptimal results. All-in-one models, though capable of handling multiple tasks, typically support only a limited range and often produce overly smooth, low-fidelity outcomes due to their broad data distribution fitting. To address these challenges, we first define a new pipeline for restoring images with multiple degradations, and then introduce RestoreAgent, an intelligent image restoration system leveraging multimodal large language models. RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration. Experimental results demonstrate the superior performance of RestoreAgent in handling complex degradation, surpassing human experts. Furthermore, the system modular design facilitates the fast integration of new tasks and models, enhancing its flexibility and scalability for various applications. |
|
| Restoring Images in Adverse Weather Conditions via Histogram Transformer | 2024-07-25 | ShowTransformer-based image restoration methods in adverse weather have achieved significant progress. Most of them use self-attention along the channel dimension or within spatially fixed-range blocks to reduce computational load. However, such a compromise results in limitations in capturing long-range spatial features. Inspired by the observation that the weather-induced degradation factors mainly cause similar occlusion and brightness, in this work, we propose an efficient Histogram Transformer (Histoformer) for restoring images affected by adverse weather. It is powered by a mechanism dubbed histogram self-attention, which sorts and segments spatial features into intensity-based bins. Self-attention is then applied across bins or within each bin to selectively focus on spatial features of dynamic range and process similar degraded pixels of the long range together. To boost histogram self-attention, we present a dynamic-range convolution enabling conventional convolution to conduct operation over similar pixels rather than neighbor pixels. We also observe that the common pixel-wise losses neglect linear association and correlation between output and ground-truth. Thus, we propose to leverage the Pearson correlation coefficient as a loss function to enforce the recovered pixels following the identical order as ground-truth. Extensive experiments demonstrate the efficacy and superiority of our proposed method. We have released the codes in Github. |
19 pa...19 pages, 7 figures, 10MB |
| CLII: Visual-Text Inpainting via Cross-Modal Predictive Interaction | 2024-07-23 | ShowImage inpainting aims to fill missing pixels in damaged images and has achieved significant progress with cut-edging learning techniques. Nevertheless, state-of-the-art inpainting methods are mainly designed for nature images and cannot correctly recover text within scene text images, and training existing models on the scene text images cannot fix the issues. In this work, we identify the visual-text inpainting task to achieve high-quality scene text image restoration and text completion: Given a scene text image with unknown missing regions and the corresponding text with unknown missing characters, we aim to complete the missing information in both images and text by leveraging their complementary information. Intuitively, the input text, even if damaged, contains language priors of the contents within the images and can guide the image inpainting. Meanwhile, the scene text image includes the appearance cues of the characters that could benefit text recovery. To this end, we design the cross-modal predictive interaction (CLII) model containing two branches, i.e., ImgBranch and TxtBranch, for scene text inpainting and text completion, respectively while leveraging their complementary effectively. Moreover, we propose to embed our model into the SOTA scene text spotting method and significantly enhance its robustness against missing pixels, which demonstrates the practicality of the newly developed task. To validate the effectiveness of our method, we construct three real datasets based on existing text-related datasets, containing 1838 images and covering three scenarios with curved, incidental, and styled texts, and conduct extensive experiments to show that our method outperforms baselines significantly. |
|
| Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems | 2024-07-23 | ShowRecent studies on inverse problems have proposed posterior samplers that leverage the pre-trained diffusion models as powerful priors. These attempts have paved the way for using diffusion models in a wide range of inverse problems. However, the existing methods entail computationally demanding iterative sampling procedures and optimize a separate solution for each measurement, which leads to limited scalability and lack of generalization capability across unseen samples. To address these limitations, we propose a novel approach, Diffusion prior-based Amortized Variational Inference (DAVI) that solves inverse problems with a diffusion prior from an amortized variational inference perspective. Specifically, instead of separate measurement-wise optimization, our amortized inference learns a function that directly maps measurements to the implicit posterior distributions of corresponding clean data, enabling a single-step posterior sampling even for unseen measurements. Extensive experiments on image restoration tasks, e.g., Gaussian deblur, 4$\times$ super-resolution, and box inpainting with two benchmark datasets, demonstrate our approach's superior performance over strong baselines. Code is available at https://github.com/mlvlab/DAVI. |
ECCV ...ECCV 2024; 41 pages, 19 figures |
| HPPP: Halpern-type Preconditioned Proximal Point Algorithms and Applications to Image Restoration | 2024-07-21 | ShowPreconditioned Proximal Point (PPP) algorithms provide a unified framework for splitting methods in image restoration. Recent advancements with RED (Regularization by Denoising) and PnP (Plug-and-Play) priors have achieved state-of-the-art performance in this domain, emphasizing the need for a meaningful particular solution. However, degenerate PPP algorithms typically exhibit weak convergence in infinite-dimensional Hilbert space, leading to uncertain solutions. To address this issue, we propose the Halpern-type Preconditioned Proximal Point (HPPP) algorithm, which leverages the strong convergence properties of Halpern iteration to achieve a particular solution. Based on the implicit regularization defined by gradient RED, we further introduce the Gradient REgularization by Denoising via HPPP called GraRED-HP3 algorithm. The HPPP algorithm is shown to have the regularity converging to a particular solution by a toy example. Additionally, experiments in image deblurring and inpainting validate the effectiveness of GraRED-HP3, showing it surpasses classical methods such as Chambolle-Pock (CP), PPP, RED, and RED-PRO. |
|
| DiffLoss: unleashing diffusion model as constraint for training image restoration network | 2024-07-21 | ShowImage restoration aims to enhance low quality images, producing high quality images that exhibit natural visual characteristics and fine semantic attributes. Recently, the diffusion model has emerged as a powerful technique for image generation, and it has been explicitly employed as a backbone in image restoration tasks, yielding excellent results. However, it suffers from the drawbacks of slow inference speed and large model parameters due to its intrinsic characteristics. In this paper, we introduce a new perspective that implicitly leverages the diffusion model to assist the training of image restoration network, called DiffLoss, which drives the restoration results to be optimized for naturalness and semantic-aware visual effect. To achieve this, we utilize the mode coverage capability of the diffusion model to approximate the distribution of natural images and explore its ability to capture image semantic attributes. On the one hand, we extract intermediate noise to leverage its modeling capability of the distribution of natural images, which serves as a naturalness-oriented optimization space. On the other hand, we utilize the bottleneck features of diffusion model to harness its semantic attributes serving as a constraint on semantic level. By combining these two designs, the overall loss function is able to improve the perceptual quality of image restoration, resulting in visually pleasing and semantically enhanced outcomes. To validate the effectiveness of our method, we conduct experiments on various common image restoration tasks and benchmarks. Extensive experimental results demonstrate that our approach enhances the visual quality and semantic perception of the restoration network. |
|
| Deep Learning CT Image Restoration using System Blur and Noise Models | 2024-07-20 | ShowThe restoration of images affected by blur and noise has been widely studied and has broad potential for applications including in medical imaging modalities like computed tomography (CT). Although the blur and noise in CT images can be attributed to a variety of system factors, these image properties can often be modeled and predicted accurately and used in classical restoration approaches for deconvolution and denoising. In classical approaches, simultaneous deconvolution and denoising can be challenging and often represent competing goals. Recently, deep learning approaches have demonstrated the potential to enhance image quality beyond classic limits; however, most deep learning models attempt a blind restoration problem and base their restoration on image inputs alone without direct knowledge of the image noise and blur properties. In this work, we present a method that leverages both degraded image inputs and a characterization of the system blur and noise to combine modeling and deep learning approaches. Different methods to integrate these auxiliary inputs are presented. Namely, an input-variant and a weight-variant approach wherein the auxiliary inputs are incorporated as a parameter vector before and after the convolutional block, respectively, allowing easy integration into any CNN architecture. The proposed model shows superior performance compared to baseline models lacking auxiliary inputs. Evaluations are based on the average Peak Signal-to-Noise Ratio (PSNR), selected examples of good and poor performance for varying approaches, and an input space analysis to assess the effect of different noise and blur on performance. Results demonstrate the efficacy of providing a deep learning model with auxiliary inputs, representing system blur and noise characteristics, to enhance the performance of the model in image restoration tasks. |
|
| Dual High-Order Total Variation Model for Underwater Image Restoration | 2024-07-20 | ShowUnderwater images are typically characterized by color cast, haze, blurring, and uneven illumination due to the selective absorption and scattering when light propagates through the water, which limits their practical applications. Underwater image enhancement and restoration (UIER) is one crucial mode to improve the visual quality of underwater images. However, most existing UIER methods concentrate on enhancing contrast and dehazing, rarely pay attention to the local illumination differences within the image caused by illumination variations, thus introducing some undesirable artifacts and unnatural color. To address this issue, an effective variational framework is proposed based on an extended underwater image formation model (UIFM). Technically, dual high-order regularizations are successfully integrated into the variational model to acquire smoothed local ambient illuminance and structure-revealed reflectance in a unified manner. In our proposed framework, the weight factors-based color compensation is combined with the color balance to compensate for the attenuated color channels and remove the color cast. In particular, the local ambient illuminance with strong robustness is acquired by performing the local patch brightest pixel estimation and an improved gamma correction. Additionally, we design an iterative optimization algorithm relying on the alternating direction method of multipliers (ADMM) to accelerate the solution of the proposed variational model. Considerable experiments on three real-world underwater image datasets demonstrate that the proposed method outperforms several state-of-the-art methods with regard to visual quality and quantitative assessments. Moreover, the proposed method can also be extended to outdoor image dehazing, low-light image enhancement, and some high-level vision tasks. The code is available at https://github.com/Hou-Guojia/UDHTV. |
13 pages, 10 figures |
| DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models | 2024-07-19 | ShowThis paper introduces a method for zero-shot video restoration using pre-trained image restoration diffusion models. Traditional video restoration methods often need retraining for different settings and struggle with limited generalization across various degradation types and datasets. Our approach uses a hierarchical token merging strategy for keyframes and local frames, combined with a hybrid correspondence mechanism that blends optical flow and feature-based nearest neighbor matching (latent merging). We show that our method not only achieves top performance in zero-shot video restoration but also significantly surpasses trained models in generalization across diverse datasets and extreme degradations (8$\times$ super-resolution and high-standard deviation video denoising). We present evidence through quantitative metrics and visual comparisons on various challenging datasets. Additionally, our technique works with any 2D restoration diffusion model, offering a versatile and powerful tool for video enhancement tasks without extensive retraining. This research leads to more efficient and widely applicable video restoration technologies, supporting advancements in fields that require high-quality video output. See our project page for video results at https://jimmycv07.github.io/DiffIR2VR_web/. |
Proje...Project page: https://jimmycv07.github.io/DiffIR2VR_web/ |
| Any Image Restoration with Efficient Automatic Degradation Adaptation | 2024-07-18 | ShowWith the emergence of mobile devices, there is a growing demand for an efficient model to restore any degraded image for better perceptual quality. However, existing models often require specific learning modules tailored for each degradation, resulting in complex architectures and high computation costs. Different from previous work, in this paper, we propose a unified manner to achieve joint embedding by leveraging the inherent similarities across various degradations for efficient and comprehensive restoration. Specifically, we first dig into the sub-latent space of each input to analyze the key components and reweight their contributions in a gated manner. The intrinsic awareness is further integrated with contextualized attention in an X-shaped scheme, maximizing local-global intertwining. Extensive comparison on benchmarking all-in-one restoration setting validates our efficiency and effectiveness, i.e., our network sets new SOTA records while reducing model complexity by approximately -82% in trainable parameters and -85% in FLOPs. Our code will be made publicly available at:https://github.com/Amazingren/AnyIR. |
Effic...Efficient Any Image Restoration |
| Energy-Calibrated VAE with Test Time Free Lunch | 2024-07-18 | ShowIn this paper, we propose a novel generative model that utilizes a conditional Energy-Based Model (EBM) for enhancing Variational Autoencoder (VAE), termed Energy-Calibrated VAE (EC-VAE). Specifically, VAEs often suffer from blurry generated samples due to the lack of a tailored training on the samples generated in the generative direction. On the other hand, EBMs can generate high-quality samples but require expensive Markov Chain Monte Carlo (MCMC) sampling. To address these issues, we introduce a conditional EBM for calibrating the generative direction of VAE during training, without requiring it for the generation at test time. In particular, we train EC-VAE upon both the input data and the calibrated samples with adaptive weight to enhance efficacy while avoiding MCMC sampling at test time. Furthermore, we extend the calibration idea of EC-VAE to variational learning and normalizing flows, and apply EC-VAE to an additional application of zero-shot image restoration via neural transport prior and range-null theory. We evaluate the proposed method with two applications, including image generation and zero-shot image restoration, and the experimental results show that our method achieves competitive performance over single-step non-adversarial generation. Our code is available at https://github.com/DJ-LYH/EC-VAE. |
ECCV ...ECCV 2024. Code is available at https://github.com/DJ-LYH/EC-VAE |
| Training-Free Large Model Priors for Multiple-in-One Image Restoration | 2024-07-18 | ShowImage restoration aims to reconstruct the latent clear images from their degraded versions. Despite the notable achievement, existing methods predominantly focus on handling specific degradation types and thus require specialized models, impeding real-world applications in dynamic degradation scenarios. To address this issue, we propose Large Model Driven Image Restoration framework (LMDIR), a novel multiple-in-one image restoration paradigm that leverages the generic priors from large multi-modal language models (MMLMs) and the pretrained diffusion models. In detail, LMDIR integrates three key prior knowledges: 1) global degradation knowledge from MMLMs, 2) scene-aware contextual descriptions generated by MMLMs, and 3) fine-grained high-quality reference images synthesized by diffusion models guided by MMLM descriptions. Standing on above priors, our architecture comprises a query-based prompt encoder, degradation-aware transformer block injecting global degradation knowledge, content-aware transformer block incorporating scene description, and reference-based transformer block incorporating fine-grained image priors. This design facilitates single-stage training paradigm to address various degradations while supporting both automatic and user-guided restoration. Extensive experiments demonstrate that our designed method outperforms state-of-the-art competitors on multiple evaluation benchmarks. |
|
| GRIDS: Grouped Multiple-Degradation Restoration with Image Degradation Similarity | 2024-07-17 | ShowTraditional single-task image restoration methods excel in handling specific degradation types but struggle with multiple degradations. To address this limitation, we propose Grouped Restoration with Image Degradation Similarity (GRIDS), a novel approach that harmonizes the competing objectives inherent in multiple-degradation restoration. We first introduce a quantitative method for assessing relationships between image degradations using statistical modeling of deep degradation representations. This analysis facilitates the strategic grouping of similar tasks, enhancing both the efficiency and effectiveness of the restoration process. Based on the degradation similarity, GRIDS divides restoration tasks into one of the optimal groups, where tasks within the same group are highly correlated. For instance, GRIDS effectively groups 11 degradation types into 4 cohesive groups. Trained models within each group show significant improvements, with an average improvement of 0.09dB over single-task upper bound models and 2.24dB over the mix-training baseline model. GRIDS incorporates an adaptive model selection mechanism for inference, automatically selecting the appropriate grouped-training model based on the input degradation. This mechanism is particularly useful for real-world scenarios with unknown degradations as it does not rely on explicit degradation classification modules. Furthermore, our method can predict model generalization ability without the need for network inference, providing valuable insights for practitioners. |
Accepted by ECCV2024 |
| A Comparative Study of Image Restoration Networks for General Backbone Network Design | 2024-07-16 | ShowDespite the significant progress made by deep models in various image restoration tasks, existing image restoration networks still face challenges in terms of task generality. An intuitive manifestation is that networks which excel in certain tasks often fail to deliver satisfactory results in others. To illustrate this point, we select five representative networks and conduct a comparative study on five classic image restoration tasks. First, we provide a detailed explanation of the characteristics of different image restoration tasks and backbone networks. Following this, we present the benchmark results and analyze the reasons behind the performance disparity of different models across various tasks. Drawing from this comparative study, we propose that a general image restoration backbone network needs to meet the functional requirements of diverse tasks. Based on this principle, we design a new general image restoration backbone network, X-Restormer. Extensive experiments demonstrate that X-Restormer possesses good task generality and achieves state-of-the-art performance across a variety of tasks. |
Accepted to ECCV2024 |
| Haze-Aware Attention Network for Single-Image Dehazing | 2024-07-16 | ShowSingle-image dehazing is a pivotal challenge in computer vision that seeks to remove haze from images and restore clean background details. Recognizing the limitations of traditional physical model-based methods and the inefficiencies of current attention-based solutions, we propose a new dehazing network combining an innovative Haze-Aware Attention Module (HAAM) with a Multiscale Frequency Enhancement Module (MFEM). The HAAM is inspired by the atmospheric scattering model, thus skillfully integrating physical principles into high-dimensional features for targeted dehazing. It picks up on latent features during the image restoration process, which gives a significant boost to the metrics, while the MFEM efficiently enhances high-frequency details, thus sidestepping wavelet or Fourier transform complexities. It employs multiscale fields to extract and emphasize key frequency components with minimal parameter overhead. Integrated into a simple U-Net framework, our Haze-Aware Attention Network (HAA-Net) for single-image dehazing significantly outperforms existing attention-based and transformer models in efficiency and effectiveness. Tested across various public datasets, the HAA-Net sets new performance benchmarks. Our work not only advances the field of image dehazing but also offers insights into the design of attention mechanisms for broader applications in computer vision. |
13 pages, 6 figures |
| SPIRE: Semantic Prompt-Driven Image Restoration | 2024-07-16 | ShowText-driven diffusion models have become increasingly popular for various image editing tasks, including inpainting, stylization, and object replacement. However, it still remains an open research problem to adopt this language-vision paradigm for more fine-level image processing tasks, such as denoising, super-resolution, deblurring, and compression artifact removal. In this paper, we develop SPIRE, a Semantic and restoration Prompt-driven Image Restoration framework that leverages natural language as a user-friendly interface to control the image restoration process. We consider the capacity of prompt information in two dimensions. First, we use content-related prompts to enhance the semantic alignment, effectively alleviating identity ambiguity in the restoration outcomes. Second, our approach is the first framework that supports fine-level instruction through language-based quantitative specification of the restoration strength, without the need for explicit task-specific design. In addition, we introduce a novel fusion mechanism that augments the existing ControlNet architecture by learning to rescale the generative prior, thereby achieving better restoration fidelity. Our extensive experiments demonstrate the superior restoration performance of SPIRE compared to the state of the arts, alongside offering the flexibility of text-based control over the restoration effects. |
Accep...Accepted by ECCV 2024; Webpage: https://chenyangqiqi.github.io/tip |
| In-Loop Filtering via Trained Look-Up Tables | 2024-07-15 | ShowIn-loop filtering (ILF) is a key technology for removing the artifacts in image/video coding standards. Recently, neural network-based in-loop filtering methods achieve remarkable coding gains beyond the capability of advanced video coding standards, which becomes a powerful coding tool candidate for future video coding standards. However, the utilization of deep neural networks brings heavy time and computational complexity, and high demands of high-performance hardware, which is challenging to apply to the general uses of coding scene. To address this limitation, inspired by explorations in image restoration, we propose an efficient and practical in-loop filtering scheme by adopting the Look-up Table (LUT). We train the DNN of in-loop filtering within a fixed filtering reference range, and cache the output values of the DNN into a LUT via traversing all possible inputs. At testing time in the coding process, the filtered pixel is generated by locating input pixels (to-be-filtered pixel with reference pixels) and interpolating cached filtered pixel values. To further enable the large filtering reference range with the limited storage cost of LUT, we introduce the enhanced indexing mechanism in the filtering process, and clipping/finetuning mechanism in the training. The proposed method is implemented into the Versatile Video Coding (VVC) reference software, VTM-11.0. Experimental results show that the ultrafast, very fast, and fast mode of the proposed method achieves on average 0.13%/0.34%/0.51%, and 0.10%/0.27%/0.39% BD-rate reduction, under the all intra (AI) and random access (RA) configurations. Especially, our method has friendly time and computational complexity, only 101%/102%-104%/108% time increase with 0.13-0.93 kMACs/pixel, and only 164-1148 KB storage cost for a single model. Our solution may shed light on the journey of practical neural network-based coding tool evolution. |
11 pages, 6 figures |
| MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration | 2024-07-15 | ShowWe present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and universality for different image codecs, e.g., JPEG and WebP; (ii) poor texture generation capability, particularly at low bitrates. Specifically, our MoE-DiffIR develops the powerful mixture-of-experts (MoE) prompt module, where some basic prompts cooperate to excavate the task-customized diffusion priors from Stable Diffusion (SD) for each compression task. Moreover, the degradation-aware routing mechanism is proposed to enable the flexible assignment of basic prompts. To activate and reuse the cross-modality generation prior of SD, we design the visual-to-text adapter for MoE-DiffIR, which aims to adapt the embedding of low-quality images from the visual domain to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on universal CIR have demonstrated the excellent robustness and texture restoration capability of our proposed MoE-DiffIR. The project can be found at https://renyulin-f.github.io/MoE-DiffIR.github.io/. |
Accep...Accepted by ECCV 2024 |
| Asymmetric Mask Scheme for Self-Supervised Real Image Denoising | 2024-07-15 | ShowIn recent years, self-supervised denoising methods have gained significant success and become critically important in the field of image restoration. Among them, the blind spot network based methods are the most typical type and have attracted the attentions of a large number of researchers. Although the introduction of blind spot operations can prevent identity mapping from noise to noise, it imposes stringent requirements on the receptive fields in the network design, thereby limiting overall performance. To address this challenge, we propose a single mask scheme for self-supervised denoising training, which eliminates the need for blind spot operation and thereby removes constraints on the network structure design. Furthermore, to achieve denoising across entire image during inference, we propose a multi-mask scheme. Our method, featuring the asymmetric mask scheme in training and inference, achieves state-of-the-art performance on existing real noisy image datasets. All the source code will be made available to the public. |
|
| Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context | 2024-07-12 | ShowPixel-wise predictions are required in a wide variety of tasks such as image restoration, image segmentation, or disparity estimation. Common models involve several stages of data resampling, in which the resolution of feature maps is first reduced to aggregate information and then increased to generate a high-resolution output. Previous works have shown that resampling operations are subject to artifacts such as aliasing. During downsampling, aliases have been shown to compromise the prediction stability of image classifiers. During upsampling, they have been leveraged to detect generated content. Yet, the effect of aliases during upsampling has not yet been discussed w.r.t. the stability and robustness of pixel-wise predictions. While falling under the same term (aliasing), the challenges for correct upsampling in neural networks differ significantly from those during downsampling: when downsampling, some high frequencies can not be correctly represented and have to be removed to avoid aliases. However, when upsampling for pixel-wise predictions, we actually require the model to restore such high frequencies that can not be encoded in lower resolutions. The application of findings from signal processing is therefore a necessary but not a sufficient condition to achieve the desirable output. In contrast, we find that the availability of large spatial context during upsampling allows to provide stable, high-quality pixel-wise predictions, even when fully learning all filter weights. |
Accep...Accepted at ECCV 2024 |
| Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution | 2024-07-12 | ShowReal-world low-resolution (LR) videos have diverse and complex degradations, imposing great challenges on video super-resolution (VSR) algorithms to reproduce their high-resolution (HR) counterparts with high quality. Recently, the diffusion models have shown compelling performance in generating realistic details for image restoration tasks. However, the diffusion process has randomness, making it hard to control the contents of restored images. This issue becomes more serious when applying diffusion models to VSR tasks because temporal consistency is crucial to the perceptual quality of videos. In this paper, we propose an effective real-world VSR algorithm by leveraging the strength of pre-trained latent diffusion models. To ensure the content consistency among adjacent frames, we exploit the temporal dynamics in LR videos to guide the diffusion process by optimizing the latent sampling path with a motion-guided loss, ensuring that the generated HR video maintains a coherent and continuous visual flow. To further mitigate the discontinuity of generated details, we insert temporal module to the decoder and fine-tune it with an innovative sequence-oriented loss. The proposed motion-guided latent diffusion (MGLD) based VSR algorithm achieves significantly better perceptual quality than state-of-the-arts on real-world VSR benchmark datasets, validating the effectiveness of the proposed model design and training strategies. |
|
| Region Attention Transformer for Medical Image Restoration | 2024-07-12 | ShowTransformer-based methods have demonstrated impressive results in medical image restoration, attributed to the multi-head self-attention (MSA) mechanism in the spatial dimension. However, the majority of existing Transformers conduct attention within fixed and coarsely partitioned regions (\text{e.g.} the entire image or fixed patches), resulting in interference from irrelevant regions and fragmentation of continuous image content. To overcome these challenges, we introduce a novel Region Attention Transformer (RAT) that utilizes a region-based multi-head self-attention mechanism (R-MSA). The R-MSA dynamically partitions the input image into non-overlapping semantic regions using the robust Segment Anything Model (SAM) and then performs self-attention within these regions. This region partitioning is more flexible and interpretable, ensuring that only pixels from similar semantic regions complement each other, thereby eliminating interference from irrelevant regions. Moreover, we introduce a focal region loss to guide our model to adaptively focus on recovering high-difficulty regions. Extensive experiments demonstrate the effectiveness of RAT in various medical image restoration tasks, including PET image synthesis, CT image denoising, and pathological image super-resolution. Code is available at \href{https://github.com/Yaziwel/Region-Attention-Transformer-for-Medical-Image-Restoration.git}{https://github.com/RAT}. |
This ...This paper has been accepted by MICCAI 2024 |
| MetaWeather: Few-Shot Weather-Degraded Image Restoration | 2024-07-12 | ShowReal-world weather conditions are intricate and often occur concurrently. However, most existing restoration approaches are limited in their applicability to specific weather conditions in training data and struggle to generalize to unseen weather types, including real-world weather conditions. To address this issue, we introduce MetaWeather, a universal approach that can handle diverse and novel weather conditions with a single unified model. Extending a powerful meta-learning framework, MetaWeather formulates the task of weather-degraded image restoration as a few-shot adaptation problem that predicts the degradation pattern of a query image, and learns to adapt to unseen weather conditions through a novel spatial-channel matching algorithm. Experimental results on the BID Task II.A, SPA-Data, and RealSnow datasets demonstrate that the proposed method can adapt to unseen weather conditions, significantly outperforming the state-of-the-art multi-weather image restoration methods. |
Accep...Accepted to ECCV 2024. Code is available at https://github.com/RangeWING/MetaWeather |
| Exploring Richer and More Accurate Information via Frequency Selection for Image Restoration | 2024-07-12 | ShowImage restoration aims to recover high-quality images from their corrupted counterparts. Many existing methods primarily focus on the spatial domain, neglecting the understanding of frequency variations and ignoring the impact of implicit noise in skip connections. In this paper, we introduce a multi-scale frequency selection network (MSFSNet) that seamlessly integrates spatial and frequency domain knowledge, selectively recovering richer and more accurate information. Specifically, we initially capture spatial features and input them into dynamic filter selection modules (DFS) at different scales to integrate frequency knowledge. DFS utilizes learnable filters to generate high and low-frequency information and employs a frequency cross-attention mechanism (FCAM) to determine the most information to recover. To learn a multi-scale and accurate set of hybrid features, we develop a skip feature fusion block (SFF) that leverages contextual features to discriminatively determine which information should be propagated in skip-connections. It is worth noting that our DFS and SFF are generic plug-in modules that can be directly employed in existing networks without any adjustments, leading to performance improvements. Extensive experiments across various image restoration tasks demonstrate that our MSFSNet achieves performance that is either superior or comparable to state-of-the-art algorithms. |
arXiv...arXiv admin note: text overlap with arXiv:2403.20106 |
| Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey | 2024-07-11 | ShowShadow removal aims at restoring the image content within shadow regions, pursuing a uniform distribution of illumination that is consistent between shadow and non-shadow regions. {Comparing to other image restoration tasks, there are two unique challenges in shadow removal:} 1) The patterns of shadows are arbitrary, varied, and often have highly complex trace structures, making ``trace-less'' image recovery difficult. 2) The degradation caused by shadows is spatially non-uniform, resulting in inconsistencies in illumination and color between shadow and non-shadow areas. Recent developments in this field are primarily driven by deep learning-based solutions, employing a variety of learning strategies, network architectures, loss functions, and training data. Nevertheless, a thorough and insightful review of deep learning-based shadow removal techniques is still lacking. In this paper, we are the first to provide a comprehensive survey to cover various aspects ranging from technical details to applications. We highlight the major advancements in deep learning-based single-image shadow removal methods, thoroughly review previous research across various categories, and provide insights into the historical progression of these developments. Additionally, we summarize performance comparisons both quantitatively and qualitatively. Beyond the technical aspects of shadow removal methods, we also explore potential future directions for this field. |
url: ... |
| Haar Nuclear Norms with Applications to Remote Sensing Imagery Restoration | 2024-07-11 | ShowRemote sensing image restoration aims to reconstruct missing or corrupted areas within images. To date, low-rank based models have garnered significant interest in this field. This paper proposes a novel low-rank regularization term, named the Haar nuclear norm (HNN), for efficient and effective remote sensing image restoration. It leverages the low-rank properties of wavelet coefficients derived from the 2-D frontal slice-wise Haar discrete wavelet transform, effectively modeling the low-rank prior for separated coarse-grained structure and fine-grained textures in the image. Experimental evaluations conducted on hyperspectral image inpainting, multi-temporal image cloud removal, and hyperspectral image denoising have revealed the HNN's potential. Typically, HNN achieves a performance improvement of 1-4 dB and a speedup of 10-28x compared to some state-of-the-art methods (e.g., tensor correlated total variation, and fully-connected tensor network) for inpainting tasks. |
|
| RPBG: Towards Robust Neural Point-based Graphics in the Wild | 2024-07-11 | ShowPoint-based representations have recently gained popularity in novel view synthesis, for their unique advantages, e.g., intuitive geometric representation, simple manipulation, and faster convergence. However, based on our observation, these point-based neural re-rendering methods are only expected to perform well under ideal conditions and suffer from noisy, patchy points and unbounded scenes, which are challenging to handle but defacto common in real applications. To this end, we revisit one such influential method, known as Neural Point-based Graphics (NPBG), as our baseline, and propose Robust Point-based Graphics (RPBG). We in-depth analyze the factors that prevent NPBG from achieving satisfactory renderings on generic datasets, and accordingly reform the pipeline to make it more robust to varying datasets in-the-wild. Inspired by the practices in image restoration, we greatly enhance the neural renderer to enable the attention-based correction of point visibility and the inpainting of incomplete rasterization, with only acceptable overheads. We also seek for a simple and lightweight alternative for environment modeling and an iterative method to alleviate the problem of poor geometry. By thorough evaluation on a wide range of datasets with different shooting conditions and camera trajectories, RPBG stably outperforms the baseline by a large margin, and exhibits its great robustness over state-of-the-art NeRF-based variants. Code available at https://github.com/QT-Zhu/RPBG. |
ECCV 2024 |
| Aging-Resistant Wideband Precoding in 5G and Beyond Using 3D Convolutional Neural Networks | 2024-07-10 | ShowTo meet the ever-increasing demand for higher data rates, 5G and 6G technologies are shifting transceivers to higher carrier frequencies, to support wider bandwidths and more antenna elements. Nevertheless, this solution poses several key challenges: i) increasing the carrier frequency and bandwidth leads to greater channel frequency selectivity in time and frequency domains, and ii) the greater the number of antennas the greater the the pilot overhead for channel estimation and the more prohibitively complex it becomes to determine the optimal precoding matrix. This paper presents two deep-learning frameworks to solve these issues. Firstly, we propose a 3D convolutional neural network (CNN) that is based on image super-resolution and captures the correlations between the transmitting and receiving antennas and the frequency domains to combat frequency selectivity. Secondly, we devise a deep learning-based framework to combat the time selectivity of the channel that treats channel aging as a distortion that can be mitigated through deep learning-based image restoration techniques. Simulation results show that combining both frameworks leads to a significant improvement in performance compared to existing techniques with little increase in complexity. |
13 pa...13 pages, 9 figures, 3 tables |
| Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization | 2024-07-09 | ShowDiffusion models have demonstrated impressive performance in various image generation, editing, enhancement and translation tasks. In particular, the pre-trained text-to-image stable diffusion models provide a potential solution to the challenging realistic image super-resolution (Real-ISR) and image stylization problems with their strong generative priors. However, the existing methods along this line often fail to keep faithful pixel-wise image structures. If extra skip connections between the encoder and the decoder of a VAE are used to reproduce details, additional training in image space will be required, limiting the application to tasks in latent space such as image stylization. In this work, we propose a pixel-aware stable diffusion (PASD) network to achieve robust Real-ISR and personalized image stylization. Specifically, a pixel-aware cross attention module is introduced to enable diffusion models perceiving image local structures in pixel-wise level, while a degradation removal module is used to extract degradation insensitive features to guide the diffusion process together with image high level information. An adjustable noise schedule is introduced to further improve the image restoration results. By simply replacing the base diffusion model with a stylized one, PASD can generate diverse stylized images without collecting pairwise training data, and by shifting the base model with an aesthetic one, PASD can bring old photos back to life. Extensive experiments in a variety of image enhancement and stylization tasks demonstrate the effectiveness of our proposed PASD approach. Our source codes are available at \url{https://github.com/yangxy/PASD/}. |
|
| InstructIR: High-Quality Image Restoration Following Human Instructions | 2024-07-07 | ShowImage restoration is a fundamental problem that involves recovering a high-quality clean image from its degraded observation. All-In-One image restoration models can effectively restore images from various types and levels of degradation using degradation-specific information as prompts to guide the restoration model. In this work, we present the first approach that uses human-written instructions to guide the image restoration model. Given natural language prompts, our model can recover high-quality images from their degraded counterparts, considering multiple degradation types. Our method, InstructIR, achieves state-of-the-art results on several restoration tasks including image denoising, deraining, deblurring, dehazing, and (low-light) image enhancement. InstructIR improves +1dB over previous all-in-one restoration methods. Moreover, our dataset and results represent a novel benchmark for new research on text-guided image restoration and enhancement. Our code, datasets and models are available at: https://github.com/mv-lab/InstructIR |
Europ...European Conference on Computer Vision (ECCV) 2024 |
| Multi-scale Conditional Generative Modeling for Microscopic Image Restoration | 2024-07-07 | ShowThe advance of diffusion-based generative models in recent years has revolutionized state-of-the-art (SOTA) techniques in a wide variety of image analysis and synthesis tasks, whereas their adaptation on image restoration, particularly within computational microscopy remains theoretically and empirically underexplored. In this research, we introduce a multi-scale generative model that enhances conditional image restoration through a novel exploitation of the Brownian Bridge process within wavelet domain. By initiating the Brownian Bridge diffusion process specifically at the lowest-frequency subband and applying generative adversarial networks at subsequent multi-scale high-frequency subbands in the wavelet domain, our method provides significant acceleration during training and sampling while sustaining a high image generation quality and diversity on par with SOTA diffusion models. Experimental results on various computational microscopy and imaging tasks confirm our method's robust performance and its considerable reduction in its sampling steps and time. This pioneering technique offers an efficient image restoration framework that harmonizes efficiency with quality, signifying a major stride in incorporating cutting-edge generative models into computational microscopy workflows. |
|
| Robust Skin Color Driven Privacy Preserving Face Recognition via Function Secret Sharing | 2024-07-06 | ShowIn this work, we leverage the pure skin color patch from the face image as the additional information to train an auxiliary skin color feature extractor and face recognition model in parallel to improve performance of state-of-the-art (SOTA) privacy-preserving face recognition (PPFR) systems. Our solution is robust against black-box attacking and well-established generative adversarial network (GAN) based image restoration. We analyze the potential risk in previous work, where the proposed cosine similarity computation might directly leak the protected precomputed embedding stored on the server side. We propose a Function Secret Sharing (FSS) based face embedding comparison protocol without any intermediate result leakage. In addition, we show in experiments that the proposed protocol is more efficient compared to the Secret Sharing (SS) based protocol. |
Accepted at ICIP2024 |
| CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks | 2024-07-05 | ShowWhile neural networks allow highly accurate predictions in many tasks, their lack of robustness towards even slight input perturbations often hampers their deployment. Adversarial attacks such as the seminal projected gradient descent (PGD) offer an effective means to evaluate a model's robustness and dedicated solutions have been proposed for attacks on semantic segmentation or optical flow estimation. While they attempt to increase the attack's efficiency, a further objective is to balance its effect, so that it acts on the entire image domain instead of isolated point-wise predictions. This often comes at the cost of optimization stability and thus efficiency. Here, we propose CosPGD, an attack that encourages more balanced errors over the entire image domain while increasing the attack's overall efficiency. To this end, CosPGD leverages a simple alignment score computed from any pixel-wise prediction and its target to scale the loss in a smooth and fully differentiable way. It leads to efficient evaluations of a model's robustness for semantic segmentation as well as regression models (such as optical flow, disparity estimation, or image restoration), and it allows it to outperform the previous SotA attack on semantic segmentation. We provide code for the CosPGD algorithm and example usage at https://github.com/shashankskagnihotri/cospgd. |
Accep...Accepted at 41st International Conference on Machine Learning (ICML), 2024 |
| On a nonlinear nonlocal reaction-diffusion system applied to image restoration | 2024-07-05 | ShowThis paper deals with a novel nonlinear coupled nonlocal reaction-diffusion system proposed for image restoration, characterized by the advantages of preserving low gray level features and textures.The gray level indicator in the proposed model is regularized using a new method based on porous media type equations, which is suitable for recovering noisy blurred images. The well-posedness, regularity, and other properties of the model are investigated, addressing the lack of theoretical analysis in those existing similar types of models. Numerical experiments conducted on texture and satellite images demonstrate the effectiveness of the proposed model in denoising and deblurring tasks. |
28 pages,7 figures |
| Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration | 2024-07-04 | ShowImage restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc. However, due to the inherent complexity and non-uniqueness of degradation in real-world images, it is challenging for a model trained for single tasks to handle real-world restoration problems effectively. Moreover, existing methods often suffer from over-smoothing and lack of realism in the restored results. To address these issues, we propose Diff-Restorer, a universal image restoration method based on the diffusion model, aiming to leverage the prior knowledge of Stable Diffusion to remove degradation while generating high perceptual quality restoration results. Specifically, we utilize the pre-trained visual language model to extract visual prompts from degraded images, including semantic and degradation embeddings. The semantic embeddings serve as content prompts to guide the diffusion model for generation. In contrast, the degradation embeddings modulate the Image-guided Control Module to generate spatial priors for controlling the spatial structure of the diffusion process, ensuring faithfulness to the original image. Additionally, we design a Degradation-aware Decoder to perform structural correction and convert the latent code to the pixel domain. We conducted comprehensive qualitative and quantitative analysis on restoration tasks with different degradations, demonstrating the effectiveness and superiority of our approach. |
|
| MRIR: Integrating Multimodal Insights for Diffusion-based Realistic Image Restoration | 2024-07-04 | ShowRealistic image restoration is a crucial task in computer vision, and the use of diffusion-based models for image restoration has garnered significant attention due to their ability to produce realistic results. However, the quality of the generated images is still a significant challenge due to the severity of image degradation and the uncontrollability of the diffusion model. In this work, we delve into the potential of utilizing pre-trained stable diffusion for image restoration and propose MRIR, a diffusion-based restoration method with multimodal insights. Specifically, we explore the problem from two perspectives: textual level and visual level. For the textual level, we harness the power of the pre-trained multimodal large language model to infer meaningful semantic information from low-quality images. Furthermore, we employ the CLIP image encoder with a designed Refine Layer to capture image details as a supplement. For the visual level, we mainly focus on the pixel level control. Thus, we utilize a Pixel-level Processor and ControlNet to control spatial structures. Finally, we integrate the aforementioned control information into the denoising U-Net using multi-level attention mechanisms and realize controllable image restoration with multimodal insights. The qualitative and quantitative results demonstrate our method's superiority over other state-of-the-art methods on both synthetic and real-world datasets. |
|
| Zero-shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model | 2024-07-02 | ShowDiffusion-based zero-shot image restoration and enhancement models have achieved great success in various image restoration and enhancement tasks without training. However, directly applying them to video restoration and enhancement results in severe temporal flickering artifacts. In this paper, we propose the first framework for zero-shot video restoration and enhancement based on a pre-trained image diffusion model. By replacing the self-attention layer with the proposed cross-previous-frame attention layer, the pre-trained image diffusion model can take advantage of the temporal correlation between neighboring frames. We further propose temporal consistency guidance, spatial-temporal noise sharing, and an early stopping sampling strategy for better temporally consistent sampling. Our method is a plug-and-play module that can be inserted into any diffusion-based zero-shot image restoration or enhancement methods to further improve their performance. Experimental results demonstrate the superiority of our proposed method in producing temporally consistent videos with better fidelity. |
19 pages |
| Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing | 2024-07-01 | ShowDiffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples from the previous step. However, this process struggles to correct errors from earlier sampling steps, leading to worse performance in complicated nonlinear inverse problems, such as phase retrieval. To address this challenge, we propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process. Specifically, we decouple consecutive steps in a diffusion sampling trajectory, allowing them to vary considerably from one another while ensuring their time-marginals anneal to the true posterior as we reduce noise levels. This approach enables the exploration of a larger solution space, improving the success rate for accurate reconstructions. We demonstrate that DAPS significantly improves sample quality and stability across multiple image restoration tasks, particularly in complicated nonlinear inverse problems. For example, we achieve a PSNR of 30.72dB on the FFHQ 256 dataset for phase retrieval, which is an improvement of 9.12dB compared to existing methods. |
|
| Blind Inversion using Latent Diffusion Priors | 2024-07-01 | ShowDiffusion models have emerged as powerful tools for solving inverse problems due to their exceptional ability to model complex prior distributions. However, existing methods predominantly assume known forward operators (i.e., non-blind), limiting their applicability in practical settings where acquiring such operators is costly. Additionally, many current approaches rely on pixel-space diffusion models, leaving the potential of more powerful latent diffusion models (LDMs) underexplored. In this paper, we introduce LatentDEM, an innovative technique that addresses more challenging blind inverse problems using latent diffusion priors. At the core of our method is solving blind inverse problems within an iterative Expectation-Maximization (EM) framework: (1) the E-step recovers clean images from corrupted observations using LDM priors and a known forward model, and (2) the M-step estimates the forward operator based on the recovered images. Additionally, we propose two novel optimization techniques tailored for LDM priors and EM frameworks, yielding more accurate and efficient blind inversion results. As a general framework, LatentDEM supports both linear and non-linear inverse problems. Beyond common 2D image restoration tasks, it enables new capabilities in non-linear 3D inverse rendering problems. We validate LatentDEM's performance on representative 2D blind deblurring and 3D sparse-view reconstruction tasks, demonstrating its superior efficacy over prior arts. |
|
| Learning Frequency-Aware Dynamic Transformers for All-In-One Image Restoration | 2024-06-30 | ShowThis work aims to tackle the all-in-one image restoration task, which seeks to handle multiple types of degradation with a single model. The primary challenge is to extract degradation representations from the input degraded images and use them to guide the model's adaptation to specific degradation types. Recognizing that various degradations affect image content differently across frequency bands, we propose a new all-in-one image restoration approach from a frequency perspective, leveraging advanced vision transformers. Our method consists of two main components: a frequency-aware Degradation prior learning transformer (Dformer) and a degradation-adaptive Restoration transformer (Rformer). The Dformer captures the essential characteristics of various degradations by decomposing inputs into different frequency components. By understanding how degradations affect these frequency components, the Dformer learns robust priors that effectively guide the restoration process. The Rformer then employs a degradation-adaptive self-attention module to selectively focus on the most affected frequency components, guided by the learned degradation representations. Extensive experimental results demonstrate that our approach outperforms the existing methods on four representative restoration tasks, including denoising, deraining, dehazing and deblurring. Additionally, our method offers benefits for handling spatially variant degradations and unseen degradation levels. |
8 pages |
| Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation | 2024-06-30 | ShowDue to the unaffordable size and intensive computation costs of low-level vision models, All-in-One models that are designed to address a handful of low-level vision tasks simultaneously have been popular. However, existing All-in-One models are limited in terms of the range of tasks and performance. To overcome these limitations, we propose Instruct-IPT -- an All-in-One Image Processing Transformer that could effectively address manifold image restoration tasks with large inter-task gaps, such as denoising, deblurring, deraining, dehazing, and desnowing. Rather than popular feature adaptation methods, we propose weight modulation that adapts weights to specific tasks. Firstly, we figure out task-sensitive weights via a toy experiment and introduce task-specific biases on top of them. Secondly, we conduct rank analysis for a good compression strategy and perform low-rank decomposition on the biases. Thirdly, we propose synchronous training that updates the task-general backbone model and the task-specific biases simultaneously. In this way, the model is instructed to learn general and task-specific knowledge. Via our simple yet effective method that instructs the IPT to be task experts, Instruct-IPT could better cooperate between tasks with distinct characteristics at humble costs. Further, we propose to maneuver Instruct-IPT with text instructions for better user interfaces. We have conducted experiments on Instruct-IPT to demonstrate the effectiveness of our method on manifold tasks, and we have effectively extended our method to diffusion denoisers as well. The code is available at https://github.com/huawei-noah/Pretrained-IPT. |
15 pages, 4 figures |
| All-In-One Medical Image Restoration via Task-Adaptive Routing | 2024-06-28 | ShowAlthough single-task medical image restoration (MedIR) has witnessed remarkable success, the limited generalizability of these methods poses a substantial obstacle to wider application. In this paper, we focus on the task of all-in-one medical image restoration, aiming to address multiple distinct MedIR tasks with a single universal model. Nonetheless, due to significant differences between different MedIR tasks, training a universal model often encounters task interference issues, where different tasks with shared parameters may conflict with each other in the gradient update direction. This task interference leads to deviation of the model update direction from the optimal path, thereby affecting the model's performance. To tackle this issue, we propose a task-adaptive routing strategy, allowing conflicting tasks to select different network paths in spatial and channel dimensions, thereby mitigating task interference. Experimental results demonstrate that our proposed \textbf{A}ll-in-one \textbf{M}edical \textbf{I}mage \textbf{R}estoration (\textbf{AMIR}) network achieves state-of-the-art performance in three MedIR tasks: MRI super-resolution, CT denoising, and PET synthesis, both in single-task and all-in-one settings. The code and data will be available at \href{https://github.com/Yaziwel/All-In-One-Medical-Image-Restoration-via-Task-Adaptive-Routing.git}{https://github.com/Yaziwel/AMIR}. |
This ...This article has been early accepted by MICCAI 2024 |
| Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration | 2024-06-26 | ShowAlthough deep learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing methods address this issue by improving data synthesis pipelines, estimating degradation kernels, employing deep internal learning, and performing domain adaptation and regularization. Previous domain adaptation methods have sought to bridge the domain gap by learning domain-invariant knowledge in either feature or pixel space. However, these techniques often struggle to extend to low-level vision tasks within a stable and compact framework. In this paper, we show that it is possible to perform domain adaptation via the noise-space using diffusion models. In particular, by leveraging the unique property of how the multi-step denoising process is influenced by auxiliary conditional inputs, we obtain meaningful gradients from noise prediction to gradually align the restored results of both synthetic and real-world data to a common clean distribution. We refer to this method as denoising as adaptation. To prevent shortcuts during training, we present useful techniques such as channel shuffling and residual-swapping contrastive learning. Experimental results on three classical image restoration tasks, namely denoising, deblurring, and deraining, demonstrate the effectiveness of the proposed method. Code will be released at: https://github.com/KangLiao929/Noise-DA/. |
Githu...Github Repository: https://github.com/KangLiao929/Noise-DA/ |
| ConStyle v2: A Strong Prompter for All-in-One Image Restoration | 2024-06-26 | ShowThis paper introduces ConStyle v2, a strong plug-and-play prompter designed to output clean visual prompts and assist U-Net Image Restoration models in handling multiple degradations. The joint training process of IRConStyle, an Image Restoration framework consisting of ConStyle and a general restoration network, is divided into two stages: first, pre-training ConStyle alone, and then freezing its weights to guide the training of the general restoration network. Three improvements are proposed in the pre-training stage to train ConStyle: unsupervised pre-training, adding a pretext task (i.e. classification), and adopting knowledge distillation. Without bells and whistles, we can get ConStyle v2, a strong prompter for all-in-one Image Restoration, in less than two GPU days and doesn't require any fine-tuning. Extensive experiments on Restormer (transformer-based), NAFNet (CNN-based), MAXIM-1S (MLP-based), and a vanilla CNN network demonstrate that ConStyle v2 can enhance any U-Net style Image Restoration models to all-in-one Image Restoration models. Furthermore, models guided by the well-trained ConStyle v2 exhibit superior performance in some specific degradation compared to ConStyle. |
|
| MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal | 2024-06-26 | ShowWhen light is scattered or reflected accidentally in the lens, flare artifacts may appear in the captured photos, affecting the photos' visual quality. The main challenge in flare removal is to eliminate various flare artifacts while preserving the original content of the image. To address this challenge, we propose a lightweight Multi-Frequency Deflare Network (MFDNet) based on the Laplacian Pyramid. Our network decomposes the flare-corrupted image into low and high-frequency bands, effectively separating the illumination and content information in the image. The low-frequency part typically contains illumination information, while the high-frequency part contains detailed content information. So our MFDNet consists of two main modules: the Low-Frequency Flare Perception Module (LFFPM) to remove flare in the low-frequency part and the Hierarchical Fusion Reconstruction Module (HFRM) to reconstruct the flare-free image. Specifically, to perceive flare from a global perspective while retaining detailed information for image restoration, LFFPM utilizes Transformer to extract global information while utilizing a convolutional neural network to capture detailed local features. Then HFRM gradually fuses the outputs of LFFPM with the high-frequency component of the image through feature aggregation. Moreover, our MFDNet can reduce the computational cost by processing in multiple frequency bands instead of directly removing the flare on the input image. Experimental results demonstrate that our approach outperforms state-of-the-art methods in removing nighttime flare on real-world and synthetic images from the Flare7K dataset. Furthermore, the computational complexity of our model is remarkably low. |
Accep...Accepted by The Visual Computer journal |
| Graph Image Prior for Unsupervised Dynamic Cardiac Cine MRI Reconstruction | 2024-06-25 | ShowThe inductive bias of the convolutional neural network (CNN) can be a strong prior for image restoration, which is known as the Deep Image Prior (DIP). Recently, DIP is utilized in unsupervised dynamic MRI reconstruction, which adopts a generative model from the latent space to the image space. However, existing methods usually use a pyramid-shaped CNN generator shared by all frames, embedding the temporal modeling within the latent space, which may hamper the model expression capability. In this work, we propose a novel scheme for dynamic MRI representation, named ``Graph Image Prior'' (GIP). GIP adopts a two-stage generative network in a new modeling methodology, which first employs independent CNNs to recover the image structure for each frame, and then exploits the spatio-temporal correlations within the feature space parameterized by a graph model. A graph convolutional network is utilized for feature fusion and dynamic image generation. In addition, we devise an ADMM algorithm to alternately optimize the images and the network parameters to improve the reconstruction performance. Experiments were conducted on cardiac cine MRI reconstruction, which demonstrate that GIP outperforms compressed sensing methods and other DIP-based unsupervised methods, significantly reducing the performance gap with state-of-the-art supervised algorithms. Moreover, GIP displays superior generalization ability when transferred to a different reconstruction setting, without the need for any additional data. |
|
| DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolution | 2024-06-24 | ShowImage super-resolution pursuits reconstructing high-fidelity high-resolution counterpart for low-resolution image. In recent years, diffusion-based models have garnered significant attention due to their capabilities with rich prior knowledge. The success of diffusion models based on general text prompts has validated the effectiveness of textual control in the field of text2image. However, given the severe degradation commonly presented in low-resolution images, coupled with the randomness characteristics of diffusion models, current models struggle to adequately discern semantic and degradation information within severely degraded images. This often leads to obstacles such as semantic loss, visual artifacts, and visual hallucinations, which pose substantial challenges for practical use. To address these challenges, this paper proposes to leverage degradation-aligned language prompt for accurate, fine-grained, and high-fidelity image restoration. Complementary priors including semantic content descriptions and degradation prompts are explored. Specifically, on one hand, image-restoration prompt alignment decoder is proposed to automatically discern the degradation degree of LR images, thereby generating beneficial degradation priors for image restoration. On the other hand, much richly tailored descriptions from pretrained multimodal large language model elicit high-level semantic priors closely aligned with human perception, ensuring fidelity control for image restoration. Comprehensive comparisons with state-of-the-art methods have been done on several popular synthetic and real-world benchmark datasets. The quantitative and qualitative analysis have demonstrated that the proposed method achieves a new state-of-the-art perceptual quality level, especially in real-world cases based on reference-free metrics. |
|
| LIR: A Lightweight Baseline for Image Restoration | 2024-06-24 | ShowRecently, there have been significant advancements in Image Restoration based on CNN and transformer. However, the inherent characteristics of the Image Restoration task are often overlooked in many works. They, instead, tend to focus on the basic block design and stack numerous such blocks to the model, leading to parameters redundant and computations unnecessary. Thus, the efficiency of the image restoration is hindered. In this paper, we propose a Lightweight Baseline network for Image Restoration called LIR to efficiently restore the image and remove degradations. First of all, through an ingenious structural design, LIR removes the degradations existing in the local and global residual connections that are ignored by modern networks. Then, a Lightweight Adaptive Attention (LAA) Block is introduced which is mainly composed of proposed Adaptive Filters and Attention Blocks. The proposed Adaptive Filter is used to adaptively extract high-frequency information and enhance object contours in various IR tasks, and Attention Block involves a novel Patch Attention module to approximate the self-attention part of the transformer. On the deraining task, our LIR achieves the state-of-the-art Structure Similarity Index Measure (SSIM) and comparable performance to state-of-the-art models on Peak Signal-to-Noise Ratio (PSNR). For denoising, dehazing, and deblurring tasks, LIR also achieves a comparable performance to state-of-the-art models with a parameter size of about 30%. In addition, it is worth noting that our LIR produces better visual results that are more in line with the human aesthetic. |
|
| Ultra-High-Definition Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution | 2024-06-22 | ShowUltra-High-Definition (UHD) image restoration has acquired remarkable attention due to its practical demand. In this paper, we construct UHD snow and rain benchmarks, named UHD-Snow and UHD-Rain, to remedy the deficiency in this field. The UHD-Snow/UHD-Rain is established by simulating the physics process of rain/snow into consideration and each benchmark contains 3200 degraded/clear image pairs of 4K resolution. Furthermore, we propose an effective UHD image restoration solution by considering gradient and normal priors in model design thanks to these priors' spatial and detail contributions. Specifically, our method contains two branches: (a) feature fusion and reconstruction branch in high-resolution space and (b) prior feature interaction branch in low-resolution space. The former learns high-resolution features and fuses prior-guided low-resolution features to reconstruct clear images, while the latter utilizes normal and gradient priors to mine useful spatial features and detail features to guide high-resolution recovery better. To better utilize these priors, we introduce single prior feature interaction and dual prior feature interaction, where the former respectively fuses normal and gradient priors with high-resolution features to enhance prior ones, while the latter calculates the similarity between enhanced prior ones and further exploits dual guided filtering to boost the feature interaction of dual priors. We conduct experiments on both new and existing public datasets and demonstrate the state-of-the-art performance of our method on UHD image low-light enhancement, UHD image desonwing, and UHD image deraining. The source codes and benchmarks are available at \url{https://github.com/wlydlut/UHDDIP}. |
| Title | Date | Abstract | Comment |
|---|---|---|---|
| SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation | 2024-09-10 | ShowIn recent years, the development of diffusion models has led to significant progress in image and video generation tasks, with pre-trained models like the Stable Diffusion series playing a crucial role. Inspired by model pruning which lightens large pre-trained models by removing unimportant parameters, we propose a novel model fine-tuning method to make full use of these ineffective parameters and enable the pre-trained model with new task-specified capabilities. In this work, we first investigate the importance of parameters in pre-trained diffusion models, and discover that the smallest 10% to 20% of parameters by absolute values do not contribute to the generation process. Based on this observation, we propose a method termed SaRA that re-utilizes these temporarily ineffective parameters, equating to optimizing a sparse weight matrix to learn the task-specific knowledge. To mitigate overfitting, we propose a nuclear-norm-based low-rank sparse training scheme for efficient fine-tuning. Furthermore, we design a new progressive parameter adjustment strategy to make full use of the re-trained/finetuned parameters. Finally, we propose a novel unstructural backpropagation strategy, which significantly reduces memory costs during fine-tuning. Our method enhances the generative capabilities of pre-trained models in downstream applications and outperforms traditional fine-tuning methods like LoRA in maintaining model's generalization ability. We validate our approach through fine-tuning experiments on SD models, demonstrating significant improvements. SaRA also offers a practical advantage that requires only a single line of code modification for efficient implementation and is seamlessly compatible with existing methods. |
Param...Parameter efficient finetuning method |
| Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models | 2024-09-10 | ShowWhile current emotional text-to-speech (TTS) systems can generate highly intelligible emotional speech, achieving fine control over emotion rendering of the output speech still remains a significant challenge. In this paper, we introduce ParaEVITS, a novel emotional TTS framework that leverages the compositionality of natural language to enhance control over emotional rendering. By incorporating a text-audio encoder inspired by ParaCLAP, a contrastive language-audio pretraining (CLAP) model for computational paralinguistics, the diffusion model is trained to generate emotional embeddings based on textual emotional style descriptions. Our framework first trains on reference audio using the audio encoder, then fine-tunes a diffusion model to process textual inputs from ParaCLAP's text encoder. During inference, speech attributes such as pitch, jitter, and loudness are manipulated using only textual conditioning. Our experiments demonstrate that ParaEVITS effectively control emotion rendering without compromising speech quality. Speech demos are publicly available. |
|
| Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition | 2024-09-10 | ShowVery low-resolution face recognition is challenging due to the serious loss of informative facial details in resolution degradation. In this paper, we propose a generative-discriminative representation distillation approach that combines generative representation with cross-resolution aligned knowledge distillation. This approach facilitates very low-resolution face recognition by jointly distilling generative and discriminative models via two distillation modules. Firstly, the generative representation distillation takes the encoder of a diffusion model pretrained for face super-resolution as the generative teacher to supervise the learning of the student backbone via feature regression, and then freezes the student backbone. After that, the discriminative representation distillation further considers a pretrained face recognizer as the discriminative teacher to supervise the learning of the student head via cross-resolution relational contrastive distillation. In this way, the general backbone representation can be transformed into discriminative head representation, leading to a robust and discriminative student model for very low-resolution face recognition. Our approach improves the recovery of the missing details in very low-resolution faces and achieves better knowledge transfer. Extensive experiments on face datasets demonstrate that our approach enhances the recognition accuracy of very low-resolution faces, showcasing its effectiveness and adaptability. |
|
| What happens to diffusion model likelihood when your model is conditional? | 2024-09-10 | ShowDiffusion Models (DMs) iteratively denoise random samples to produce high-quality data. The iterative sampling process is derived from Stochastic Differential Equations (SDEs), allowing a speed-quality trade-off chosen at inference. Another advantage of sampling with differential equations is exact likelihood computation. These likelihoods have been used to rank unconditional DMs and for out-of-domain classification. Despite the many existing and possible uses of DM likelihoods, the distinct properties captured are unknown, especially in conditional contexts such as Text-To-Image (TTI) or Text-To-Speech synthesis (TTS). Surprisingly, we find that TTS DM likelihoods are agnostic to the text input. TTI likelihood is more expressive but cannot discern confounding prompts. Our results show that applying DMs to conditional tasks reveals inconsistencies and strengthens claims that the properties of DM likelihood are unknown. This impact sheds light on the previously unknown nature of DM likelihoods. Although conditional DMs maximise likelihood, the likelihood in question is not as sensitive to the conditioning input as one expects. This investigation provides a new point-of-view on diffusion likelihoods. |
|
| DiffQRCoder: Diffusion-based Aesthetic QR Code Generation with Scanning Robustness Guided Iterative Refinement | 2024-09-10 | ShowWith the success of Diffusion Models for image generation, the technologies also have revolutionized the aesthetic Quick Response (QR) code generation. Despite significant improvements in visual attractiveness for the beautified codes, their scannabilities are usually sacrificed and thus hinder their practical uses in real-world scenarios. To address this issue, we propose a novel Diffusion-based QR Code generator (DiffQRCoder) to effectively craft both scannable and visually pleasing QR codes. The proposed approach introduces Scanning-Robust Perceptual Guidance (SRPG), a new diffusion guidance for Diffusion Models to guarantee the generated aesthetic codes to obey the ground-truth QR codes while maintaining their attractiveness during the denoising process. Additionally, we present another post-processing technique, Scanning Robust Manifold Projected Gradient Descent (SR-MPGD), to further enhance their scanning robustness through iterative latent space optimization. With extensive experiments, the results demonstrate that our approach not only outperforms other compared methods in Scanning Success Rate (SSR) with better or comparable CLIP aesthetic score (CLIP-aes.) but also significantly improves the SSR of the ControlNet-only approach from 60% to 99%. The subjective evaluation indicates that our approach achieves promising visual attractiveness to users as well. Finally, even with different scanning angles and the most rigorous error tolerance settings, our approach robustly achieves over 95% SSR, demonstrating its capability for real-world applications. |
|
| Diff-INR: Generative Regularization for Electrical Impedance Tomography | 2024-09-10 | ShowElectrical Impedance Tomography (EIT) is a non-invasive imaging technique that reconstructs conductivity distributions within a body from boundary measurements. However, EIT reconstruction is hindered by its ill-posed nonlinear inverse problem, which complicates accurate results. To tackle this, we propose Diff-INR, a novel method that combines generative regularization with Implicit Neural Representations (INR) through a diffusion model. Diff-INR introduces geometric priors to guide the reconstruction, effectively addressing the shortcomings of traditional regularization methods. By integrating a pre-trained diffusion regularizer with INR, our approach achieves state-of-the-art reconstruction accuracy in both simulation and experimental data. The method demonstrates robust performance across various mesh densities and hyperparameter settings, highlighting its flexibility and efficiency. This advancement represents a significant improvement in managing the ill-posed nature of EIT. Furthermore, the method's principles are applicable to other imaging modalities facing similar challenges with ill-posed inverse problems. |
|
| SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillation | 2024-09-10 | ShowDespite their ability to generate high-resolution and diverse images from text prompts, text-to-image diffusion models often suffer from slow iterative sampling processes. Model distillation is one of the most effective directions to accelerate these models. However, previous distillation methods fail to retain the generation quality while requiring a significant amount of images for training, either from real data or synthetically generated by the teacher model. In response to this limitation, we present a novel image-free distillation scheme named |
Accep...Accepted to CVPR 2024; Github: https://github.com/VinAIResearch/SwiftBrush |
| RangeLDM: Fast Realistic LiDAR Point Cloud Generation | 2024-09-10 | ShowAutonomous driving demands high-quality LiDAR data, yet the cost of physical LiDAR sensors presents a significant scaling-up challenge. While recent efforts have explored deep generative models to address this issue, they often consume substantial computational resources with slow generation speeds while suffering from a lack of realism. To address these limitations, we introduce RangeLDM, a novel approach for rapidly generating high-quality range-view LiDAR point clouds via latent diffusion models. We achieve this by correcting range-view data distribution for accurate projection from point clouds to range images via Hough voting, which has a critical impact on generative learning. We then compress the range images into a latent space with a variational autoencoder, and leverage a diffusion model to enhance expressivity. Additionally, we instruct the model to preserve 3D structural fidelity by devising a range-guided discriminator. Experimental results on KITTI-360 and nuScenes datasets demonstrate both the robust expressiveness and fast speed of our LiDAR point cloud generation. |
|
| Multi-Source Music Generation with Latent Diffusion | 2024-09-10 | ShowMost music generation models directly generate a single music mixture. To allow for more flexible and controllable generation, the Multi-Source Diffusion Model (MSDM) has been proposed to model music as a mixture of multiple instrumental sources (e.g., piano, drums, bass, and guitar). Its goal is to use one single diffusion model to generate consistent music sources, which are further mixed to form the music. Despite its capabilities, MSDM is unable to generate songs with rich melodies and often generates empty sounds. Also, its waveform diffusion introduces significant Gaussian noise artifacts, which compromises audio quality. In response, we introduce a multi-source latent diffusion model (MSLDM) that employs Variational Autoencoders (VAEs) to encode each instrumental source into a distinct latent representation. By training a VAE on all music sources, we efficiently capture each source's unique characteristics in a source latent that our diffusion model models jointly. This approach significantly enhances the total and partial generation of music by leveraging the VAE's latent compression and noise-robustness. The compressed source latent also facilitates more efficient generation. Subjective listening tests and Frechet Audio Distance (FAD) scores confirm that our model outperforms MSDM, showcasing its practical and enhanced applicability in music generation systems. We also emphasize that modeling sources is more effective than direct music mixture modeling. Codes and models are available at https://github.com/XZWY/MSLDM. Demos are available at https://xzwy.github.io/MSLDMDemo. |
ICASS...ICASSP 2025 in Submission |
| MyGo: Consistent and Controllable Multi-View Driving Video Generation with Camera Control | 2024-09-10 | ShowHigh-quality driving video generation is crucial for providing training data for autonomous driving models. However, current generative models rarely focus on enhancing camera motion control under multi-view tasks, which is essential for driving video generation. Therefore, we propose MyGo, an end-to-end framework for video generation, introducing motion of onboard cameras as conditions to make progress in camera controllability and multi-view consistency. MyGo employs additional plug-in modules to inject camera parameters into the pre-trained video diffusion model, which retains the extensive knowledge of the pre-trained model as much as possible. Furthermore, we use epipolar constraints and neighbor view information during the generation process of each view to enhance spatial-temporal consistency. Experimental results show that MyGo has achieved state-of-the-art results in both general camera-controlled video generation and multi-view driving video generation tasks, which lays the foundation for more accurate environment simulation in autonomous driving. Project page: \href{https://metadrivescape.github.io/papers_project/MyGo/page.html}{metadrivescape.github.io/papers\_project/MyGo/page.html} |
|
| Make-A-Shape: a Ten-Million-scale 3D Shape Model | 2024-09-10 | ShowSignificant progress has been made in training large generative models for natural language and images. Yet, the advancement of 3D generative models is hindered by their substantial resource demands for training, along with inefficient, non-compact, and less expressive representations. This paper introduces Make-A-Shape, a new 3D generative model designed for efficient training on a vast scale, capable of utilizing 10 millions publicly-available shapes. Technical-wise, we first innovate a wavelet-tree representation to compactly encode shapes by formulating the subband coefficient filtering scheme to efficiently exploit coefficient relations. We then make the representation generatable by a diffusion model by devising the subband coefficients packing scheme to layout the representation in a low-resolution grid. Further, we derive the subband adaptive training strategy to train our model to effectively learn to generate coarse and detail wavelet coefficients. Last, we extend our framework to be controlled by additional input conditions to enable it to generate shapes from assorted modalities, e.g., single/multi-view images, point clouds, and low-resolution voxels. In our extensive set of experiments, we demonstrate various applications, such as unconditional generation, shape completion, and conditional generation on a wide range of modalities. Our approach not only surpasses the state of the art in delivering high-quality results but also efficiently generates shapes within a few seconds, often achieving this in just 2 seconds for most conditions. Our source code is available at https://github.com/AutodeskAILab/Make-a-Shape. |
|
| EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation | 2024-09-10 | ShowDue to their text-to-image synthesis feature, diffusion models have recently seen a rise in visual perception tasks, such as depth estimation. The lack of good-quality datasets makes the extraction of a fine-grain semantic context challenging for the diffusion models. The semantic context with fewer details further worsens the process of creating effective text embeddings that will be used as input for diffusion models. In this paper, we propose a novel EDADepth, an enhanced data augmentation method to estimate monocular depth without using additional training data. We use Swin2SR, a super-resolution model, to enhance the quality of input images. We employ the BEiT pre-trained semantic segmentation model for better extraction of text embeddings. We introduce BLIP-2 tokenizer to generate tokens from these text embeddings. The novelty of our approach is the introduction of Swin2SR, the BEiT model, and the BLIP-2 tokenizer in the diffusion-based pipeline for the monocular depth estimation. Our model achieves state-of-the-art results (SOTA) on the {\delta}3 metric on NYUv2 and KITTI datasets. It also achieves results comparable to those of the SOTA models in the RMSE and REL metrics. Finally, we also show improvements in the visualization of the estimated depth compared to the SOTA diffusion-based monocular depth estimation models. Code: https://github.com/edadepthmde/EDADepth_ICMLA. |
|
| Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer | 2024-09-09 | ShowMusic timbre transfer is a challenging task that involves modifying the timbral characteristics of an audio signal while preserving its melodic structure. In this paper, we propose a novel method based on dual diffusion bridges, trained using the CocoChorales Dataset, which consists of unpaired monophonic single-instrument audio data. Each diffusion model is trained on a specific instrument with a Gaussian prior. During inference, a model is designated as the source model to map the input audio to its corresponding Gaussian prior, and another model is designated as the target model to reconstruct the target audio from this Gaussian prior, thereby facilitating timbre transfer. We compare our approach against existing unsupervised timbre transfer models such as VAEGAN and Gaussian Flow Bridges (GFB). Experimental results demonstrate that our method achieves both better Fr'echet Audio Distance (FAD) and melody preservation, as reflected by lower pitch distances (DPD) compared to VAEGAN and GFB. Additionally, we discover that the noise level from the Gaussian prior, |
|
| SVS-GAN: Leveraging GANs for Semantic Video Synthesis | 2024-09-09 | ShowIn recent years, there has been a growing interest in Semantic Image Synthesis (SIS) through the use of Generative Adversarial Networks (GANs) and diffusion models. This field has seen innovations such as the implementation of specialized loss functions tailored for this task, diverging from the more general approaches in Image-to-Image (I2I) translation. While the concept of Semantic Video Synthesis (SVS)$\unicode{x2013}$the generation of temporally coherent, realistic sequences of images from semantic maps$\unicode{x2013}$is newly formalized in this paper, some existing methods have already explored aspects of this field. Most of these approaches rely on generic loss functions designed for video-to-video translation or require additional data to achieve temporal coherence. In this paper, we introduce the SVS-GAN, a framework specifically designed for SVS, featuring a custom architecture and loss functions. Our approach includes a triple-pyramid generator that utilizes SPADE blocks. Additionally, we employ a U-Net-based network for the image discriminator, which performs semantic segmentation for the OASIS loss. Through this combination of tailored architecture and objective engineering, our framework aims to bridge the existing gap between SIS and SVS, outperforming current state-of-the-art models on datasets like Cityscapes and KITTI-360. |
|
| DiffusionPen: Towards Controlling the Style of Handwritten Text Generation | 2024-09-09 | ShowHandwritten Text Generation (HTG) conditioned on text and style is a challenging task due to the variability of inter-user characteristics and the unlimited combinations of characters that form new words unseen during training. Diffusion Models have recently shown promising results in HTG but still remain under-explored. We present DiffusionPen (DiffPen), a 5-shot style handwritten text generation approach based on Latent Diffusion Models. By utilizing a hybrid style extractor that combines metric learning and classification, our approach manages to capture both textual and stylistic characteristics of seen and unseen words and styles, generating realistic handwritten samples. Moreover, we explore several variation strategies of the data with multi-style mixtures and noisy embeddings, enhancing the robustness and diversity of the generated data. Extensive experiments using IAM offline handwriting database show that our method outperforms existing methods qualitatively and quantitatively, and its additional generated data can improve the performance of Handwriting Text Recognition (HTR) systems. The code is available at: https://github.com/koninik/DiffusionPen. |
|
| ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models | 2024-09-09 | ShowDiffusion models have demonstrated exceptional capabilities in generating a broad spectrum of visual content, yet their proficiency in rendering text is still limited: they often generate inaccurate characters or words that fail to blend well with the underlying image. To address these shortcomings, we introduce a new framework named ARTIST. This framework incorporates a dedicated textual diffusion model to specifically focus on the learning of text structures. Initially, we pretrain this textual model to capture the intricacies of text representation. Subsequently, we finetune a visual diffusion model, enabling it to assimilate textual structure information from the pretrained textual model. This disentangled architecture design and the training strategy significantly enhance the text rendering ability of the diffusion models for text-rich image generation. Additionally, we leverage the capabilities of pretrained large language models to better interpret user intentions, contributing to improved generation quality. Empirical results on the MARIO-Eval benchmark underscore the effectiveness of the proposed method, showing an improvement of up to 15% in various metrics. |
|
| Enhanced Generative Data Augmentation for Semantic Segmentation via Stronger Guidance | 2024-09-09 | ShowData augmentation is a widely used technique for creating training data for tasks that require labeled data, such as semantic segmentation. This method benefits pixel-wise annotation tasks requiring much effort and intensive labor. Traditional data augmentation methods involve simple transformations like rotations and flips to create new images from existing ones. However, these new images may lack diversity along the main semantic axes in the data and not change high-level semantic properties. To address this issue, generative models have emerged as an effective solution for augmenting data by generating synthetic images. Controllable generative models offer a way to augment data for semantic segmentation tasks using a prompt and visual reference from the original image. However, using these models directly presents challenges, such as creating an effective prompt and visual reference to generate a synthetic image that accurately reflects the content and structure of the original. In this work, we introduce an effective data augmentation method for semantic segmentation using the Controllable Diffusion Model. Our proposed method includes efficient prompt generation using Class-Prompt Appending and Visual Prior Combination to enhance attention to labeled classes in real images. These techniques allow us to generate images that accurately depict segmented classes in the real image. In addition, we employ the class balancing algorithm to ensure efficiency when merging the synthetic and original images to generate balanced data for the training dataset. We evaluated our method on the PASCAL VOC datasets and found it highly effective for synthesizing images in semantic segmentation. |
|
| CoDiCast: Conditional Diffusion Model for Weather Prediction with Uncertainty Quantification | 2024-09-09 | ShowAccurate weather forecasting is critical for science and society. Yet, existing methods have not managed to simultaneously have the properties of high accuracy, low uncertainty, and high computational efficiency. On one hand, to quantify the uncertainty in weather predictions, the strategy of ensemble forecast (i.e., generating a set of diverse predictions) is often employed. However, traditional ensemble numerical weather prediction (NWP) is computationally intensive. On the other hand, most existing machine learning-based weather prediction (MLWP) approaches are efficient and accurate. Nevertheless, they are deterministic and cannot capture the uncertainty of weather forecasting. In this work, we propose CoDiCast, a conditional diffusion model to generate accurate global weather prediction, while achieving uncertainty quantification with ensemble forecasts and modest computational cost. The key idea is to simulate a conditional version of the reverse denoising process in diffusion models, which starts from pure Gaussian noise to generate realistic weather scenarios for a future time point. Each denoising step is conditioned on observations from the recent past. Ensemble forecasts are achieved by repeatedly sampling from stochastic Gaussian noise to represent uncertainty quantification. CoDiCast is trained on a decade of ERA5 reanalysis data from the European Centre for Medium-Range Weather Forecasts (ECMWF). Experimental results demonstrate that our approach outperforms several existing data-driven methods in accuracy. Our conditional diffusion model, CoDiCast, can generate 3-day global weather forecasts, at 6-hour steps and |
|
| Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing | 2024-09-09 | ShowDespite recent advances in large-scale text-to-image generative models, manipulating real images with these models remains a challenging problem. The main limitations of existing editing methods are that they either fail to perform with consistent quality on a wide range of image edits or require time-consuming hyperparameter tuning or fine-tuning of the diffusion model to preserve the image-specific appearance of the input image. We propose a novel approach that is built upon a modified diffusion sampling process via the guidance mechanism. In this work, we explore the self-guidance technique to preserve the overall structure of the input image and its local regions appearance that should not be edited. In particular, we explicitly introduce layout-preserving energy functions that are aimed to save local and global structures of the source image. Additionally, we propose a noise rescaling mechanism that allows to preserve noise distribution by balancing the norms of classifier-free guidance and our proposed guiders during generation. Such a guiding approach does not require fine-tuning the diffusion model and exact inversion process. As a result, the proposed method provides a fast and high-quality editing mechanism. In our experiments, we show through human evaluation and quantitative analysis that the proposed method allows to produce desired editing which is more preferable by humans and also achieves a better trade-off between editing quality and preservation of the original image. Our code is available at https://github.com/FusionBrainLab/Guide-and-Rescale. |
Accep...Accepted to ECCV 2024. The project page is available at https://fusionbrainlab.github.io/Guide-and-Rescale |
| Improving Antibody Design with Force-Guided Sampling in Diffusion Models | 2024-09-09 | ShowAntibodies, crucial for immune defense, primarily rely on complementarity-determining regions (CDRs) to bind and neutralize antigens, such as viruses. The design of these CDRs determines the antibody's affinity and specificity towards its target. Generative models, particularly denoising diffusion probabilistic models (DDPMs), have shown potential to advance the structure-based design of CDR regions. However, only a limited dataset of bound antibody-antigen structures is available, and generalization to out-of-distribution interfaces remains a challenge. Physics based force-fields, which approximate atomic interactions, offer a coarse but universal source of information to better mold designs to target interfaces. Integrating this foundational information into diffusion models is, therefore, highly desirable. Here, we propose a novel approach to enhance the sampling process of diffusion models by integrating force field energy-based feedback. Our model, DiffForce, employs forces to guide the diffusion sampling process, effectively blending the two distributions. Through extensive experiments, we demonstrate that our method guides the model to sample CDRs with lower energy, enhancing both the structure and sequence of the generated antibodies. |
|
| Enhancing Preference-based Linear Bandits via Human Response Time | 2024-09-09 | ShowBinary human choice feedback is widely used in interactive preference learning for its simplicity, but it provides limited information about preference strength. To overcome this limitation, we leverage human response times, which inversely correlate with preference strength, as complementary information. Our work integrates the EZ-diffusion model, which jointly models human choices and response times, into preference-based linear bandits. We introduce a computationally efficient utility estimator that reformulates the utility estimation problem using both choices and response times as a linear regression problem. Theoretical and empirical comparisons with traditional choice-only estimators reveal that for queries with strong preferences ("easy" queries), choices alone provide limited information, while response times offer valuable complementary information about preference strength. As a result, incorporating response times makes easy queries more useful. We demonstrate this advantage in the fixed-budget best-arm identification problem, with simulations based on three real-world datasets, consistently showing accelerated learning when response times are incorporated. |
|
| Vector Quantized Diffusion Model Based Speech Bandwidth Extension | 2024-09-09 | ShowRecent advancements in neural audio codec (NAC) unlock new potential in audio signal processing. Studies have increasingly explored leveraging the latent features of NAC for various speech signal processing tasks. This paper introduces the first approach to speech bandwidth extension (BWE) that utilizes the discrete features obtained from NAC. By restoring high-frequency details within highly compressed discrete tokens, this approach enhances speech intelligibility and naturalness. Based on Vector Quantized Diffusion, the proposed framework combines the strengths of advanced NAC, diffusion models, and Mamba-2 to reconstruct high-frequency speech components. Extensive experiments demonstrate that this method exhibits superior performance across both log-spectral distance and ViSQOL, significantly improving speech quality. |
4pages |
| Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion Models | 2024-09-09 | ShowText-to-image (T2I) diffusion models have become prominent tools for generating high-fidelity images from text prompts. However, when trained on unfiltered internet data, these models can produce unsafe, incorrect, or stylistically undesirable images that are not aligned with human preferences. To address this, recent approaches have incorporated human preference datasets to fine-tune T2I models or to optimize reward functions that capture these preferences. Although effective, these methods are vulnerable to reward hacking, where the model overfits to the reward function, leading to a loss of diversity in the generated images. In this paper, we prove the inevitability of reward hacking and study natural regularization techniques like KL divergence and LoRA scaling, and their limitations for diffusion models. We also introduce Annealed Importance Guidance (AIG), an inference-time regularization inspired by Annealed Importance Sampling, which retains the diversity of the base model while achieving Pareto-Optimal reward-diversity tradeoffs. Our experiments demonstrate the benefits of AIG for Stable Diffusion models, striking the optimal balance between reward optimization and image diversity. Furthermore, a user study confirms that AIG improves diversity and quality of generated images across different model architectures and reward functions. |
|
| pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning | 2024-09-09 | ShowFederated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server. Traditional methods, such as Federated Averaging (FedAvg), linearly aggregate these parameters which are usually trained on heterogeneous data distributions, potentially overlooking the complex, high-dimensional nature of the parameter space. This can result in degraded performance of the aggregated model. While personalized FL approaches can mitigate the heterogeneous data issue to some extent, the limitation of linear aggregation remains unresolved. To alleviate this issue, we investigate the generative approach of diffusion model and propose a novel generative parameter aggregation framework for personalized FL, \texttt{pFedGPA}. In this framework, we deploy a diffusion model on the server to integrate the diverse parameter distributions and propose a parameter inversion method to efficiently generate a set of personalized parameters for each client. This inversion method transforms the uploaded parameters into a latent code, which is then aggregated through denoising sampling to produce the final personalized parameters. By encoding the dependence of a client's model parameters on the specific data distribution using the high-capacity diffusion model, \texttt{pFedGPA} can effectively decouple the complexity of the overall distribution of all clients' model parameters from the complexity of each individual client's parameter distribution. Our experimental results consistently demonstrate the superior performance of the proposed method across multiple datasets, surpassing baseline approaches. |
|
| Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models | 2024-09-09 | ShowRecent research has seen significant interest in methods for concept removal and targeted forgetting in diffusion models. In this paper, we conduct a comprehensive white-box analysis to expose significant vulnerabilities in existing diffusion model unlearning methods. We show that the objective functions used for unlearning in the existing methods lead to decoupling of the targeted concepts (meant to be forgotten) for the corresponding prompts. This is concealment and not actual unlearning, which was the original goal. The ineffectiveness of current methods stems primarily from their narrow focus on reducing generation probabilities for specific prompt sets, neglecting the diverse modalities of intermediate guidance employed during the inference process. The paper presents a rigorous theoretical and empirical examination of four commonly used techniques for unlearning in diffusion models. We introduce two new evaluation metrics: Concept Retrieval Score (CRS) and Concept Confidence Score (CCS). These metrics are based on a successful adversarial attack setup that can recover forgotten concepts from unlearned diffusion models. The CRS measures the similarity between the latent representations of the unlearned and fully trained models after unlearning. It reports the extent of retrieval of the forgotten concepts with increasing amount of guidance. The CCS quantifies the confidence of the model in assigning the target concept to the manipulated data. It reports the probability of the unlearned model's generations to be aligned with the original domain knowledge with increasing amount of guidance. Evaluating existing unlearning methods with our proposed stringent metrics for diffusion models reveals significant shortcomings in their ability to truly unlearn concepts. Source Code: https://respailab.github.io/unlearning-or-concealment |
|
| Forward KL Regularized Preference Optimization for Aligning Diffusion Policies | 2024-09-09 | ShowDiffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with human intents in various tasks. To achieve this, previous methods conduct return-conditioned policy generation or Reinforcement Learning (RL)-based policy optimization, while they both rely on pre-defined reward functions. In this work, we propose a novel framework, Forward KL regularized Preference optimization for aligning Diffusion policies, to align the diffusion policy with preferences directly. We first train a diffusion policy from the offline dataset without considering the preference, and then align the policy to the preference data via direct preference optimization. During the alignment phase, we formulate direct preference learning in a diffusion policy, where the forward KL regularization is employed in preference optimization to avoid generating out-of-distribution actions. We conduct extensive experiments for MetaWorld manipulation and D4RL tasks. The results show our method exhibits superior alignment with preferences and outperforms previous state-of-the-art algorithms. |
|
| OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model | 2024-09-09 | ShowVariational Autoencoder (VAE), compressing videos into latent representations, is a crucial preceding component of Latent Video Diffusion Models (LVDMs). With the same reconstruction quality, the more sufficient the VAE's compression for videos is, the more efficient the LVDMs are. However, most LVDMs utilize 2D image VAE, whose compression for videos is only in the spatial dimension and often ignored in the temporal dimension. How to conduct temporal compression for videos in a VAE to obtain more concise latent representations while promising accurate reconstruction is seldom explored. To fill this gap, we propose an omni-dimension compression VAE, named OD-VAE, which can temporally and spatially compress videos. Although OD-VAE's more sufficient compression brings a great challenge to video reconstruction, it can still achieve high reconstructed accuracy by our fine design. To obtain a better trade-off between video reconstruction quality and compression speed, four variants of OD-VAE are introduced and analyzed. In addition, a novel tail initialization is designed to train OD-VAE more efficiently, and a novel inference strategy is proposed to enable OD-VAE to handle videos of arbitrary length with limited GPU memory. Comprehensive experiments on video reconstruction and LVDM-based video generation demonstrate the effectiveness and efficiency of our proposed methods. |
|
| Rolling Diffusion Models | 2024-09-09 | ShowDiffusion models have recently been increasingly applied to temporal data such as video, fluid mechanics simulations, or climate data. These methods generally treat subsequent frames equally regarding the amount of noise in the diffusion process. This paper explores Rolling Diffusion: a new approach that uses a sliding window denoising process. It ensures that the diffusion process progressively corrupts through time by assigning more noise to frames that appear later in a sequence, reflecting greater uncertainty about the future as the generation process unfolds. Empirically, we show that when the temporal dynamics are complex, Rolling Diffusion is superior to standard diffusion. In particular, this result is demonstrated in a video prediction task using the Kinetics-600 video dataset and in a chaotic fluid dynamics forecasting experiment. |
|
| HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts | 2024-09-09 | ShowThe potential for higher-resolution image generation using pretrained diffusion models is immense, yet these models often struggle with issues of object repetition and structural artifacts especially when scaling to 4K resolution and higher. We figure out that the problem is caused by that, a single prompt for the generation of multiple scales provides insufficient efficacy. In response, we propose HiPrompt, a new tuning-free solution that tackles the above problems by introducing hierarchical prompts. The hierarchical prompts offer both global and local guidance. Specifically, the global guidance comes from the user input that describes the overall content, while the local guidance utilizes patch-wise descriptions from MLLMs to elaborately guide the regional structure and texture generation. Furthermore, during the inverse denoising process, the generated noise is decomposed into low- and high-frequency spatial components. These components are conditioned on multiple prompt levels, including detailed patch-wise descriptions and broader image-level prompts, facilitating prompt-guided denoising under hierarchical semantic guidance. It further allows the generation to focus more on local spatial regions and ensures the generated images maintain coherent local and global semantics, structures, and textures with high definition. Extensive experiments demonstrate that HiPrompt outperforms state-of-the-art works in higher-resolution image generation, significantly reducing object repetition and enhancing structural quality. |
|
| CipherDM: Secure Three-Party Inference for Diffusion Model Sampling | 2024-09-09 | ShowDiffusion Models (DMs) achieve state-of-the-art synthesis results in image generation and have been applied to various fields. However, DMs sometimes seriously violate user privacy during usage, making the protection of privacy an urgent issue. Using traditional privacy computing schemes like Secure Multi-Party Computation (MPC) directly in DMs faces significant computation and communication challenges. To address these issues, we propose CipherDM, the first novel, versatile and universal framework applying MPC technology to DMs for secure sampling, which can be widely implemented on multiple DM based tasks. We thoroughly analyze sampling latency breakdown, find time-consuming parts and design corresponding secure MPC protocols for computing nonlinear activations including SoftMax, SiLU and Mish. CipherDM is evaluated on popular architectures (DDPM, DDIM) using MNIST dataset and on SD deployed by diffusers. Compared to direct implementation on SPU, our approach improves running time by approximately 1.084\times \sim 2.328\times, and reduces communication costs by approximately 1.212\times \sim 1.791\times. |
|
| Sequential Posterior Sampling with Diffusion Models | 2024-09-09 | ShowDiffusion models have quickly risen in popularity for their ability to model complex distributions and perform effective posterior sampling. Unfortunately, the iterative nature of these generative models makes them computationally expensive and unsuitable for real-time sequential inverse problems such as ultrasound imaging. Considering the strong temporal structure across sequences of frames, we propose a novel approach that models the transition dynamics to improve the efficiency of sequential diffusion posterior sampling in conditional image synthesis. Through modeling sequence data using a video vision transformer (ViViT) transition model based on previous diffusion outputs, we can initialize the reverse diffusion trajectory at a lower noise scale, greatly reducing the number of iterations required for convergence. We demonstrate the effectiveness of our approach on a real-world dataset of high frame rate cardiac ultrasound images and show that it achieves the same performance as a full diffusion trajectory while accelerating inference 25$\times$, enabling real-time posterior sampling. Furthermore, we show that the addition of a transition model improves the PSNR up to 8% in cases with severe motion. Our method opens up new possibilities for real-time applications of diffusion models in imaging and other domains requiring real-time inference. |
5 pag...5 pages, 4 figures, preprint |
| GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection | 2024-09-09 | ShowDiffusion models have shown superior performance on unsupervised anomaly detection tasks. Since trained with normal data only, diffusion models tend to reconstruct normal counterparts of test images with certain noises added. However, these methods treat all potential anomalies equally, which may cause two main problems. From the global perspective, the difficulty of reconstructing images with different anomalies is uneven. Therefore, instead of utilizing the same setting for all samples, we propose to predict a particular denoising step for each sample by evaluating the difference between image contents and the priors extracted from diffusion models. From the local perspective, reconstructing abnormal regions differs from normal areas even in the same image. Theoretically, the diffusion model predicts a noise for each step, typically following a standard Gaussian distribution. However, due to the difference between the anomaly and its potential normal counterpart, the predicted noise in abnormal regions will inevitably deviate from the standard Gaussian distribution. To this end, we propose introducing synthetic abnormal samples in training to encourage the diffusion models to break through the limitation of standard Gaussian distribution, and a spatial-adaptive feature fusion scheme is utilized during inference. With the above modifications, we propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection, which introduces appealing flexibility and achieves anomaly-free reconstruction while retaining as much normal information as possible. Extensive experiments are conducted on three commonly used anomaly detection datasets (MVTec-AD, MPDD, and VisA) and a printed circuit board dataset (PCB-Bank) we integrated, showing the effectiveness of the proposed method. |
Accep...Accepted by ECCV 2024, code and models: https://github.com/hyao1/GLAD. Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file |
| Diffusion-Occ: 3D Point Cloud Completion via Occupancy Diffusion | 2024-09-09 | ShowPoint clouds are crucial for capturing three-dimensional data but often suffer from incompleteness due to limitations such as resolution and occlusion. Traditional methods typically rely on point-based approaches within discriminative frameworks for point cloud completion. In this paper, we introduce \textbf{Diffusion-Occ}, a novel framework for Diffusion Point Cloud Completion. Diffusion-Occ utilizes a two-stage coarse-to-fine approach. In the first stage, the Coarse Density Voxel Prediction Network (CDNet) processes partial points to predict coarse density voxels, streamlining global feature extraction through voxel classification, as opposed to previous regression-based methods. In the second stage, we introduce the Occupancy Generation Network (OccGen), a conditional occupancy diffusion model based on a transformer architecture and enhanced by our Point-Voxel Fuse (PVF) block. This block integrates coarse density voxels with partial points to leverage both global and local features for comprehensive completion. By thresholding the occupancy field, we convert it into a complete point cloud. Additionally, our method employs diverse training mixtures and efficient diffusion parameterization to enable effective one-step sampling during both training and inference. Experimental results demonstrate that Diffusion-Occ outperforms existing discriminative and generative methods. |
After...After a closer examination of our work, we've determined that our experiments are not thorough and robust enough, possibly impacting the accuracy of our conclusions. Hence, we've decided to withdraw our article and, after refining our experiments, intend to resubmit the paper once significant improvements have been made |
| Animate3D: Animating Any 3D Model with Multi-view Video Diffusion | 2024-09-09 | ShowRecent advances in 4D generation mainly focus on generating 4D content by distilling pre-trained text or single-view image-conditioned models. It is inconvenient for them to take advantage of various off-the-shelf 3D assets with multi-view attributes, and their results suffer from spatiotemporal inconsistency owing to the inherent ambiguity in the supervision signals. In this work, we present Animate3D, a novel framework for animating any static 3D model. The core idea is two-fold: 1) We propose a novel multi-view video diffusion model (MV-VDM) conditioned on multi-view renderings of the static 3D object, which is trained on our presented large-scale multi-view video dataset (MV-Video). 2) Based on MV-VDM, we introduce a framework combining reconstruction and 4D Score Distillation Sampling (4D-SDS) to leverage the multi-view video diffusion priors for animating 3D objects. Specifically, for MV-VDM, we design a new spatiotemporal attention module to enhance spatial and temporal consistency by integrating 3D and video diffusion models. Additionally, we leverage the static 3D model's multi-view renderings as conditions to preserve its identity. For animating 3D models, an effective two-stage pipeline is proposed: we first reconstruct motions directly from generated multi-view videos, followed by the introduced 4D-SDS to refine both appearance and motion. Benefiting from accurate motion learning, we could achieve straightforward mesh animation. Qualitative and quantitative experiments demonstrate that Animate3D significantly outperforms previous approaches. Data, code, and models will be open-released. |
Proje...Project Page: https://animate3d.github.io/ |
| TPA3D: Triplane Attention for Fast Text-to-3D Generation | 2024-09-09 | ShowDue to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization time for both training and inference, the use of GAN-based models would still be desirable for fast 3D generation. In this work, we propose Triplane Attention for text-guided 3D generation (TPA3D), an end-to-end trainable GAN-based deep learning model for fast text-to-3D generation. With only 3D shape data and their rendered 2D images observed during training, our TPA3D is designed to retrieve detailed visual descriptions for synthesizing the corresponding 3D mesh data. This is achieved by the proposed attention mechanisms on the extracted sentence and word-level text features. In our experiments, we show that TPA3D generates high-quality 3D textured shapes aligned with fine-grained descriptions, while impressive computation efficiency can be observed. |
ECCV2...ECCV2024, Project Page: https://redxouls.github.io/TPA3D/ |
| TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors | 2024-09-09 | ShowDiffusion models have achieved notable success in image generation, but they remain highly vulnerable to backdoor attacks, which compromise their integrity by producing specific undesirable outputs when presented with a pre-defined trigger. In this paper, we investigate how to protect diffusion models from this dangerous threat. Specifically, we propose TERD, a backdoor defense framework that builds unified modeling for current attacks, which enables us to derive an accessible reversed loss. A trigger reversion strategy is further employed: an initial approximation of the trigger through noise sampled from a prior distribution, followed by refinement through differential multi-step samplers. Additionally, with the reversed trigger, we propose backdoor detection from the noise space, introducing the first backdoor input detection approach for diffusion models and a novel model detection algorithm that calculates the KL divergence between reversed and benign distributions. Extensive evaluations demonstrate that TERD secures a 100% True Positive Rate (TPR) and True Negative Rate (TNR) across datasets of varying resolutions. TERD also demonstrates nice adaptability to other Stochastic Differential Equation (SDE)-based models. Our code is available at https://github.com/PKU-ML/TERD. |
|
| Diffusion Cocktail: Mixing Domain-Specific Diffusion Models for Diversified Image Generations | 2024-09-09 | ShowDiffusion models, capable of high-quality image generation, receive unparalleled popularity for their ease of extension. Active users have created a massive collection of domain-specific diffusion models by fine-tuning base models on self-collected datasets. Recent work has focused on improving a single diffusion model by uncovering semantic and visual information encoded in various architecture components. However, those methods overlook the vastly available set of fine-tuned diffusion models and, therefore, miss the opportunity to utilize their combined capacity for novel generation. In this work, we propose Diffusion Cocktail (Ditail), a training-free method that transfers style and content information between multiple diffusion models. This allows us to perform diversified generations using a set of diffusion models, resulting in novel images unobtainable by a single model. Ditail also offers fine-grained control of the generation process, which enables flexible manipulations of styles and contents. With these properties, Ditail excels in numerous applications, including style transfer guided by diffusion models, novel-style image generation, and image manipulation via prompts or collage inputs. |
Proje...Project Page: https://maps-research.github.io/Ditail/ |
| Scaling Diffusion Transformers to 16 Billion Parameters | 2024-09-09 | ShowIn this paper, we present DiT-MoE, a sparse version of the diffusion Transformer, that is scalable and competitive with dense networks while exhibiting highly optimized inference. The DiT-MoE includes two simple designs: shared expert routing and expert-level balance loss, thereby capturing common knowledge and reducing redundancy among the different routed experts. When applied to conditional image generation, a deep analysis of experts specialization gains some interesting observations: (i) Expert selection shows preference with spatial position and denoising time step, while insensitive with different class-conditional information; (ii) As the MoE layers go deeper, the selection of experts gradually shifts from specific spacial position to dispersion and balance. (iii) Expert specialization tends to be more concentrated at the early time step and then gradually uniform after half. We attribute it to the diffusion process that first models the low-frequency spatial information and then high-frequency complex information. Based on the above guidance, a series of DiT-MoE experimentally achieves performance on par with dense networks yet requires much less computational load during inference. More encouragingly, we demonstrate the potential of DiT-MoE with synthesized image data, scaling diffusion model at a 16.5B parameter that attains a new SoTA FID-50K score of 1.80 in 512$\times$512 resolution settings. The project page: https://github.com/feizc/DiT-MoE. |
|
| Evaluating the design space of diffusion-based generative models | 2024-09-08 | ShowMost existing theoretical investigations of the accuracy of diffusion models, albeit significant, assume the score function has been approximated to a certain accuracy, and then use this a priori bound to control the error of generation. This article instead provides a first quantitative understanding of the whole generation process, i.e., both training and sampling. More precisely, it conducts a non-asymptotic convergence analysis of denoising score matching under gradient descent. In addition, a refined sampling error analysis for variance exploding models is also provided. The combination of these two results yields a full error analysis, which elucidates (again, but this time theoretically) how to design the training and sampling processes for effective generation. For instance, our theory implies a preference toward noise distribution and loss weighting in training that qualitatively agree with the ones used in [Karras et al. 2022]. It also provides perspectives on the choices of time and variance schedules in sampling: when the score is well trained, the design in [Song et al. 2020] is more preferable, but when it is less trained, the design in [Karras et al. 2022] becomes more preferable. |
Comme...Comments are welcome. Out of admiration we titled our paper after EDM, and hoped theorists' humor is not too corny |
| A Survey on Diffusion Models for Recommender Systems | 2024-09-08 | ShowWhile traditional recommendation techniques have made significant strides in the past decades, they still suffer from limited generalization performance caused by factors like inadequate collaborative signals, weak latent representations, and noisy data. In response, diffusion models (DMs) have emerged as promising solutions for recommender systems due to their robust generative capabilities, solid theoretical foundations, and improved training stability. To this end, in this paper, we present the first comprehensive survey on diffusion models for recommendation, and draw a bird's-eye view from the perspective of the whole pipeline in real-world recommender systems. We systematically categorize existing research works into three primary domains: (1) diffusion for data engineering & encoding, focusing on data augmentation and representation enhancement; (2) diffusion as recommender models, employing diffusion models to directly estimate user preferences and rank items; and (3) diffusion for content presentation, utilizing diffusion models to generate personalized content such as fashion and advertisement creatives. Our taxonomy highlights the unique strengths of diffusion models in capturing complex data distributions and generating high-quality, diverse samples that closely align with user preferences. We also summarize the core characteristics of the adapting diffusion models for recommendation, and further identify key areas for future exploration, which helps establish a roadmap for researchers and practitioners seeking to advance recommender systems through the innovative application of diffusion models. To further facilitate the research community of recommender systems based on diffusion models, we actively maintain a GitHub repository for papers and other related resources in this rising direction https://github.com/CHIANGEL/Awesome-Diffusion-for-RecSys. |
Under Review |
| DiffUHaul: A Training-Free Method for Object Dragging in Images | 2024-09-08 | ShowText-to-image diffusion models have proven effective for solving many image editing tasks. However, the seemingly straightforward task of seamlessly relocating objects within a scene remains surprisingly challenging. Existing methods addressing this problem often struggle to function reliably in real-world scenarios due to lacking spatial reasoning. In this work, we propose a training-free method, dubbed DiffUHaul, that harnesses the spatial understanding of a localized text-to-image model, for the object dragging task. Blindly manipulating layout inputs of the localized model tends to cause low editing performance due to the intrinsic entanglement of object representation in the model. To this end, we first apply attention masking in each denoising step to make the generation more disentangled across different objects and adopt the self-attention sharing mechanism to preserve the high-level object appearance. Furthermore, we propose a new diffusion anchoring technique: in the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance; in the later denoising steps, we pass the localized features from the source images to the interpolated images to retain fine-grained object details. To adapt DiffUHaul to real-image editing, we apply a DDPM self-attention bucketing that can better reconstruct real images with the localized model. Finally, we introduce an automated evaluation pipeline for this task and showcase the efficacy of our method. Our results are reinforced through a user preference study. |
Accep...Accepted to SIGGRAPH Asia 2024. Project page is available at https://omriavrahami.com/diffuhaul/ |
| Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images | 2024-09-08 | ShowDiffusion models (DMs) have revolutionized image generation, producing high-quality images with applications spanning various fields. However, their ability to create hyper-realistic images poses significant challenges in distinguishing between real and synthetic content, raising concerns about digital authenticity and potential misuse in creating deepfakes. This work introduces a robust detection framework that integrates image and text features extracted by CLIP model with a Multilayer Perceptron (MLP) classifier. We propose a novel loss that can improve the detector's robustness and handle imbalanced datasets. Additionally, we flatten the loss landscape during the model training to improve the detector's generalization capabilities. The effectiveness of our method, which outperforms traditional detection techniques, is demonstrated through extensive experiments, underscoring its potential to set a new state-of-the-art approach in DM-generated image detection. The code is available at https://github.com/Purdue-M2/Robust_DM_Generated_Image_Detection. |
|
| Towards Generative Class Prompt Learning for Fine-grained Visual Recognition | 2024-09-07 | ShowAlthough foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-grained categorization. Moreover, foundational models trained on one domain do not generalize well on a different domain without fine-tuning. We attribute these to the limitations of the VLM's semantic representations and attempt to improve their fine-grained visual awareness using generative modeling. Specifically, we propose two novel methods: Generative Class Prompt Learning (GCPL) and Contrastive Multi-class Prompt Learning (CoMPLe). Utilizing text-to-image diffusion models, GCPL significantly improves the visio-linguistic synergy in class embeddings by conditioning on few-shot exemplars with learnable class prompts. CoMPLe builds on this foundation by introducing a contrastive learning component that encourages inter-class separation during the generative optimization process. Our empirical results demonstrate that such a generative class prompt learning approach substantially outperform existing methods, offering a better alternative to few shot image recognition challenges. The source code will be made available at: https://github.com/soumitri2001/GCPL. |
Accep...Accepted in BMVC 2024 |
| Plug-and-Hide: Provable and Adjustable Diffusion Generative Steganography | 2024-09-07 | ShowGenerative Steganography (GS) is a novel technique that utilizes generative models to conceal messages without relying on cover images. Contemporary GS algorithms leverage the powerful generative capabilities of Diffusion Models (DMs) to create high-fidelity stego images. However, these algorithms, while yielding relatively satisfactory generation outcomes and message extraction accuracy, significantly alter modifications to the initial Gaussian noise of DMs, thereby compromising steganographic security. In this paper, we rethink the trade-off among image quality, steganographic security, and message extraction accuracy within Diffusion Generative Steganography (DGS) settings. Our findings reveal that the normality of initial noise of DMs is crucial to these factors and can offer theoretically grounded guidance for DGS design. Based on this insight, we propose a Provable and Adjustable Message Mapping (PA-B2G) approach. It can, on one hand, theoretically guarantee reversible encoding of bit messages from arbitrary distributions into standard Gaussian noise for DMs. On the other hand, its adjustability provides a more natural and fine-grained way to trade off image quality, steganographic security, and message extraction accuracy. By integrating PA-B2G with a probability flow ordinary differential equation, we establish an invertible mapping between secret messages and stego images. PA-B2G can be seamlessly incorporated with most mainstream DMs, such as the Stable Diffusion, without necessitating additional training or fine-tuning. Comprehensive experiments corroborate our theoretical insights regarding the trade-off in DGS settings and demonstrate the effectiveness of our DGS algorithm in producing high-quality stego images while preserving desired levels of steganographic security and extraction accuracy. |
|
| Reward-Directed Score-Based Diffusion Models via q-Learning | 2024-09-07 | ShowWe propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the unknown target data distributions. Different from most existing studies, our formulation does not involve any pretrained model for the unknown score functions of the noise-perturbed data distributions. We present an entropy-regularized continuous-time RL problem and show that the optimal stochastic policy has a Gaussian distribution with a known covariance matrix. Based on this result, we parameterize the mean of Gaussian policies and develop an actor-critic type (little) q-learning algorithm to solve the RL problem. A key ingredient in our algorithm design is to obtain noisy observations from the unknown score function via a ratio estimator. Numerically, we show the effectiveness of our approach by comparing its performance with two state-of-the-art RL methods that fine-tune pretrained models. Finally, we discuss extensions of our RL formulation to probability flow ODE implementation of diffusion models and to conditional diffusion models. |
|
| MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning | 2024-09-07 | ShowDiffusion models have emerged as frontrunners in text-to-image generation, however, their fixed image resolution during training often leads to challenges in high-resolution image generation, such as semantic deviations and object replication. This paper introduces MegaFusion, a novel approach that extends existing diffusion-based text-to-image generation models towards efficient higher-resolution generation without additional fine-tuning or extra adaptation. Specifically, we employ an innovative truncate and relay strategy to bridge the denoising processes across different resolutions, allowing for high-resolution image generation in a coarse-to-fine manner. Moreover, by integrating dilated convolutions and noise re-scheduling, we further adapt the model's priors for higher resolution. The versatility and efficacy of MegaFusion make it universally applicable to both latent-space and pixel-space diffusion models, along with other derivative models. Extensive experiments confirm that MegaFusion significantly boosts the capability of existing models to produce images of megapixels and various aspect ratios, while only requiring about 40% of the original computational cost. |
Techn...Technical Report. Project Page: https://haoningwu3639.github.io/MegaFusion/ |
| SpotActor: Training-Free Layout-Controlled Consistent Image Generation | 2024-09-07 | ShowText-to-image diffusion models significantly enhance the efficiency of artistic creation with high-fidelity image generation. However, in typical application scenarios like comic book production, they can neither place each subject into its expected spot nor maintain the consistent appearance of each subject across images. For these issues, we pioneer a novel task, Layout-to-Consistent-Image (L2CI) generation, which produces consistent and compositional images in accordance with the given layout conditions and text prompts. To accomplish this challenging task, we present a new formalization of dual energy guidance with optimization in a dual semantic-latent space and thus propose a training-free pipeline, SpotActor, which features a layout-conditioned backward update stage and a consistent forward sampling stage. In the backward stage, we innovate a nuanced layout energy function to mimic the attention activations with a sigmoid-like objective. While in the forward stage, we design Regional Interconnection Self-Attention (RISA) and Semantic Fusion Cross-Attention (SFCA) mechanisms that allow mutual interactions across images. To evaluate the performance, we present ActorBench, a specified benchmark with hundreds of reasonable prompt-box pairs stemming from object detection datasets. Comprehensive experiments are conducted to demonstrate the effectiveness of our method. The results prove that SpotActor fulfills the expectations of this task and showcases the potential for practical applications with superior layout alignment, subject consistency, prompt conformity and background diversity. |
|
| OneActor: Consistent Character Generation via Cluster-Conditioned Guidance | 2024-09-07 | ShowText-to-image diffusion models benefit artists with high-quality image generation. Yet their stochastic nature hinders artists from creating consistent images of the same subject. Existing methods try to tackle this challenge and generate consistent content in various ways. However, they either depend on external restricted data or require expensive tuning of the diffusion model. For this issue, we propose a novel one-shot tuning paradigm, termed as OneActor. It efficiently performs consistent subject generation solely driven by prompts via a learned semantic guidance to bypass the laborious backbone tuning. We lead the way to formalize the objective of consistent subject generation from a clustering perspective, and thus design a cluster-conditioned model. To mitigate the overfitting challenge shared by one-shot tuning pipelines, we augment the tuning with auxiliary samples and devise two inference strategies: semantic interpolation and cluster guidance. These techniques are later verified to significantly enhance the generation quality. Comprehensive experiments show that our method outperforms a variety of baselines with satisfactory subject consistency, superior prompt conformity as well as high image quality. Our method is capable of multi-subject generation and compatible with popular diffusion extensions. Besides, we achieve a 4 times faster tuning speed than tuning-based baselines and, if desired, avoid increasing inference time. Furthermore, to our best knowledge, we are the first to prove that the semantic space of the diffusion model has the same interpolation property as the latent space does. This property can serve as another promising tool for fine generation control. |
|
| Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization | 2024-09-07 | ShowRecent advancements in reinforcement learning (RL) have been fueled by large-scale data and deep neural networks, particularly for high-dimensional and complex tasks. Online RL methods like Proximal Policy Optimization (PPO) are effective in dynamic scenarios but require substantial real-time data, posing challenges in resource-constrained or slow simulation environments. Offline RL addresses this by pre-learning policies from large datasets, though its success depends on the quality and diversity of the data. This work proposes a framework that enhances PPO algorithms by incorporating a diffusion model to generate high-quality virtual trajectories for offline datasets. This approach improves exploration and sample efficiency, leading to significant gains in cumulative rewards, convergence speed, and strategy stability in complex tasks. Our contributions are threefold: we explore the potential of diffusion models in RL, particularly for offline datasets, extend the application of online RL to offline environments, and experimentally validate the performance improvements of PPO with diffusion models. These findings provide new insights and methods for applying RL to high-dimensional, complex tasks. Finally, we open-source our code at https://github.com/TianciGao/DiffPPO |
|
| Training-Free Style Consistent Image Synthesis with Condition and Mask Guidance in E-Commerce | 2024-09-07 | ShowGenerating style-consistent images is a common task in the e-commerce field, and current methods are largely based on diffusion models, which have achieved excellent results. This paper introduces the concept of the QKV (query/key/value) level, referring to modifications in the attention maps (self-attention and cross-attention) when integrating UNet with image conditions. Without disrupting the product's main composition in e-commerce images, we aim to use a train-free method guided by pre-set conditions. This involves using shared KV to enhance similarity in cross-attention and generating mask guidance from the attention map to cleverly direct the generation of style-consistent images. Our method has shown promising results in practical applications. |
|
| Tutorial on Diffusion Models for Imaging and Vision | 2024-09-06 | ShowThe astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of diffusion, a particular sampling mechanism that has overcome some shortcomings that were deemed difficult in the previous approaches. The goal of this tutorial is to discuss the essential ideas underlying the diffusion models. The target audience of this tutorial includes undergraduate and graduate students who are interested in doing research on diffusion models or applying these models to solve other problems. |
|
| Thinking Outside the BBox: Unconstrained Generative Object Compositing | 2024-09-06 | ShowCompositing an object into an image involves multiple non-trivial sub-tasks such as object placement and scaling, color/lighting harmonization, viewpoint/geometry adjustment, and shadow/reflection generation. Recent generative image compositing methods leverage diffusion models to handle multiple sub-tasks at once. However, existing models face limitations due to their reliance on masking the original object during training, which constrains their generation to the input mask. Furthermore, obtaining an accurate input mask specifying the location and scale of the object in a new image can be highly challenging. To overcome such limitations, we define a novel problem of unconstrained generative object compositing, i.e., the generation is not bounded by the mask, and train a diffusion-based model on a synthesized paired dataset. Our first-of-its-kind model is able to generate object effects such as shadows and reflections that go beyond the mask, enhancing image realism. Additionally, if an empty mask is provided, our model automatically places the object in diverse natural locations and scales, accelerating the compositing workflow. Our model outperforms existing object placement and compositing models in various quality metrics and user studies. |
|
| VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation | 2024-09-06 | ShowVILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for understanding and generating visual content, which can lead to misalignment and increased complexity. In contrast, VILA-U employs a single autoregressive next-token prediction framework for both tasks, eliminating the need for additional components like diffusion models. This approach not only simplifies the model but also achieves near state-of-the-art performance in visual language understanding and generation. The success of VILA-U is attributed to two main factors: the unified vision tower that aligns discrete visual tokens with textual inputs during pretraining, which enhances visual perception, and autoregressive image generation can achieve similar quality as diffusion models with high-quality dataset. This allows VILA-U to perform comparably to more complex models using a fully token-based autoregressive framework. |
11 pa...11 pages, 7 figures, 8 tables |
| Exploring Foundation Models for Synthetic Medical Imaging: A Study on Chest X-Rays and Fine-Tuning Techniques | 2024-09-06 | ShowMachine learning has significantly advanced healthcare by aiding in disease prevention and treatment identification. However, accessing patient data can be challenging due to privacy concerns and strict regulations. Generating synthetic, realistic data offers a potential solution for overcoming these limitations, and recent studies suggest that fine-tuning foundation models can produce such data effectively. In this study, we explore the potential of foundation models for generating realistic medical images, particularly chest x-rays, and assess how their performance improves with fine-tuning. We propose using a Latent Diffusion Model, starting with a pre-trained foundation model and refining it through various configurations. Additionally, we performed experiments with input from a medical professional to assess the realism of the images produced by each trained model. |
|
| Training-Free Condition Video Diffusion Models for single frame Spatial-Semantic Echocardiogram Synthesis | 2024-09-06 | ShowConditional video diffusion models (CDM) have shown promising results for video synthesis, potentially enabling the generation of realistic echocardiograms to address the problem of data scarcity. However, current CDMs require a paired segmentation map and echocardiogram dataset. We present a new method called Free-Echo for generating realistic echocardiograms from a single end-diastolic segmentation map without additional training data. Our method is based on the 3D-Unet with Temporal Attention Layers model and is conditioned on the segmentation map using a training-free conditioning method based on SDEdit. We evaluate our model on two public echocardiogram datasets, CAMUS and EchoNet-Dynamic. We show that our model can generate plausible echocardiograms that are spatially aligned with the input segmentation map, achieving performance comparable to training-based CDMs. Our work opens up new possibilities for generating echocardiograms from a single segmentation map, which can be used for data augmentation, domain adaptation, and other applications in medical imaging. Our code is available at \url{https://github.com/gungui98/echo-free} |
Accep...Accepted to MICCAI 2024 |
| How Fair is Your Diffusion Recommender Model? | 2024-09-06 | ShowDiffusion-based recommender systems have recently proven to outperform traditional generative recommendation approaches, such as variational autoencoders and generative adversarial networks. Nevertheless, the machine learning literature has raised several concerns regarding the possibility that diffusion models, while learning the distribution of data samples, may inadvertently carry information bias and lead to unfair outcomes. In light of this aspect, and considering the relevance that fairness has held in recommendations over the last few decades, we conduct one of the first fairness investigations in the literature on DiffRec, a pioneer approach in diffusion-based recommendation. First, we propose an experimental setting involving DiffRec (and its variant L-DiffRec) along with nine state-of-the-art recommendation models, two popular recommendation datasets from the fairness-aware literature, and six metrics accounting for accuracy and consumer/provider fairness. Then, we perform a twofold analysis, one assessing models' performance under accuracy and recommendation fairness separately, and the other identifying if and to what extent such metrics can strike a performance trade-off. Experimental results from both studies confirm the initial unfairness warnings but pave the way for how to address them in future research directions. |
|
| Zero-Shot Video Editing through Adaptive Sliding Score Distillation | 2024-09-06 | ShowThe rapidly evolving field of Text-to-Video generation (T2V) has catalyzed renewed interest in controllable video editing research. While the application of editing prompts to guide diffusion model denoising has gained prominence, mirroring advancements in image editing, this noise-based inference process inherently compromises the original video's integrity, resulting in unintended over-editing and temporal discontinuities. To address these challenges, this study proposes a novel paradigm of video-based score distillation, facilitating direct manipulation of original video content. Specifically, distinguishing it from image-based score distillation, we propose an Adaptive Sliding Score Distillation strategy, which incorporates both global and local video guidance to reduce the impact of editing errors. Combined with our proposed Image-based Joint Guidance mechanism, it has the ability to mitigate the inherent instability of the T2V model and single-step sampling. Additionally, we design a Weighted Attention Fusion module to further preserve the key features of the original video and avoid over-editing. Extensive experiments demonstrate that these strategies effectively address existing challenges, achieving superior performance compared to current state-of-the-art methods. |
|
| UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization | 2024-09-06 | ShowThis paper presents UniPortrait, an innovative human image personalization framework that unifies single- and multi-ID customization with high face fidelity, extensive facial editability, free-form input description, and diverse layout generation. UniPortrait consists of only two plug-and-play modules: an ID embedding module and an ID routing module. The ID embedding module extracts versatile editable facial features with a decoupling strategy for each ID and embeds them into the context space of diffusion models. The ID routing module then combines and distributes these embeddings adaptively to their respective regions within the synthesized image, achieving the customization of single and multiple IDs. With a carefully designed two-stage training scheme, UniPortrait achieves superior performance in both single- and multi-ID customization. Quantitative and qualitative experiments demonstrate the advantages of our method over existing approaches as well as its good scalability, e.g., the universal compatibility with existing generative control tools. The project page is at https://aigcdesigngroup.github.io/UniPortrait-Page/ . |
Tech ...Tech report; Project page: https://aigcdesigngroup.github.io/UniPortrait-Page/ |
| Geospecific View Generation -- Geometry-Context Aware High-resolution Ground View Inference from Satellite Views | 2024-09-06 | ShowPredicting realistic ground views from satellite imagery in urban scenes is a challenging task due to the significant view gaps between satellite and ground-view images. We propose a novel pipeline to tackle this challenge, by generating geospecifc views that maximally respect the weak geometry and texture from multi-view satellite images. Different from existing approaches that hallucinate images from cues such as partial semantics or geometry from overhead satellite images, our method directly predicts ground-view images at geolocation by using a comprehensive set of information from the satellite image, resulting in ground-level images with a resolution boost at a factor of ten or more. We leverage a novel building refinement method to reduce geometric distortions in satellite data at ground level, which ensures the creation of accurate conditions for view synthesis using diffusion networks. Moreover, we proposed a novel geospecific prior, which prompts distribution learning of diffusion models to respect image samples that are closer to the geolocation of the predicted images. We demonstrate our pipeline is the first to generate close-to-real and geospecific ground views merely based on satellite images. |
11 figures |
| GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers | 2024-09-06 | ShowReconstructing realistic 3D human models from monocular images has significant applications in creative industries, human-computer interfaces, and healthcare. We base our work on 3D Gaussian Splatting (3DGS), a scene representation composed of a mixture of Gaussians. Predicting such mixtures for a human from a single input image is challenging, as it is a non-uniform density (with a many-to-one relationship with input pixels) with strict physical constraints. At the same time, it needs to be flexible to accommodate a variety of clothes and poses. Our key observation is that the vertices of standardized human meshes (such as SMPL) can provide an adequate density and approximate initial position for Gaussians. We can then train a transformer model to jointly predict comparatively small adjustments to these positions, as well as the other Gaussians' attributes and the SMPL parameters. We show empirically that this combination (using only multi-view supervision) can achieve fast inference of 3D human models from a single image without test-time optimization, expensive diffusion models, or 3D points supervision. We also show that it can improve 3D pose estimation by better fitting human models that account for clothes and other variations. The code is available on the project website https://abdullahamdi.com/gst/ . |
preprint |
| Training-free Camera Control for Video Generation | 2024-09-06 | ShowWe propose a training-free and robust solution to offer camera movement control for off-the-shelf video diffusion models. Unlike previous work, our method does not require any s |