Notice！

Busy with recent things , I'll update without day.

Notes are attached to raw PDF files to save time .

CV--PaperDaily

	知乎论文阅读专栏	个人博客	其他
ming71	论文笔记入口	chaser	CSDN

Update CV papers here everday .
The contents include but are not limited to Object detection , Semantic segmentation , and other papers about deep learning . Comments are welcome , and you can e-mail me by [email protected] .

Paper reading

Divided by Conference & Journal .

Reordered via year of publications from now on, unclassified papers are preprints on arXiv .

---

2020

• [CVPR] PolarMask : Single Shot Instance Segmentation with Polar Representation
• [CVPR] Revisiting the Sibling Head in Object Detector
• [CVPR] Delving into Online High-quality Anchors Mining for Detecting Outer Faces
• [CVPR] Multiple Anchor Learning for Visual Object Detection
• [CVPR] Detection in Crowded Scenes One Proposal, Multiple Predictions
• [CVPR] Learning from Noisy Anchors for One-stage Object Detection
• [ECCV] Dynamic R-CNN : Towards High Quality Object Detection via Dynamic Training
• [AAAI] Distance-IoU
• [AAAI] Progressive Feature Polishing Network for Salient Object Detection
• [Neurocomputing] Recent Advances in Deep Learning for Object Detection
• [Neurocomputing] Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
• [WACV] Propose-and-Attend Single Shot Detector
• [WACV] Improving Object Detection with Inverted Attention
• [BMVC] Cascade RetinaNet: Maintaining Consistency for Single-Stage Object Detection
• Scale-Invariant Multi-Oriented Text Detection in Wild Scene Images
• Cross-layer Feature Pyramid Network for Salient Object Detection
• FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings
• Objects detection for remote sensing images based on polar coordinates
• Conditional Convolutions for Instance Segmentation
• 1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
• Extended Feature Pyramid Network for Small Object Detection
• Joint Anchor-Feature Refinement for Real-Time Accurate Object Detection in Images and Videos
• Location-Aware Feature Selection for Scene Text Detection
• Feature Pyramid Grids

---

2019

• [AAAI] M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid
• [AAAI] Gradient Harmonized Single-stage Detector
• [CVPR] Libra R-CNN: Towards Balanced Learning for Object Detection
• [CVPR] Assisted Excitation of Activations: A Learning Technique to Improve Object
• [CVPR] Borrow from Anywhere Pseudo Multi-modal Object Detection in Thermal Imagery
• [CVPR] Region Proposal by Guided Anchoring
• [CVPR] Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
• [CVPR] Panoptic Segmentation
• [CVPR] Learning Instance Activation Maps for Weakly Supervised Instance Segmentation
• [CVPR] Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
• [CVPR] ScratchDet : Training Single-Shot Object Detectors
• [CVPR] Dual Attention Network for Scene Segmentation
• [CVPR] Softer-NMS: Rethinking Bounding Box Regression for Accurate Object Detection
• [CVPR] Spatial-aware Graph Relation Network for Large-scale Object Detection
• [CVPR] Learning RoI Transformer for Detecting Oriented Objects in Aerial Images
• [ICCV] InstaBoost: Boosting Instance Segmentation via Probability Map Guided
• [ICCV] Scale-Aware Trident Networks for Object Detection
• [ICCV] EGNet: Edge Guidance Network for Salient Object Detection
• [ICCV] ThunderNet: Towards Real-time Generic Object Detection
• [ICCV] FCOS: Fully Convolutional One-Stage Object Detection
• [ICCV] Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving
• [ICCV] Towards More Robust Detection for Small, Cluttered and Rotated Objects
• [ICCV] Dynamic Multi-scale Filters for Semantic Segmentation
• [ICCV] Matrix Nets: A New Deep Architecture for Object Detection
• [ICML] Making Convolutional Networks Shift-Invariant Again
• [ICML] How much real data do we actually need: Analyzing object detection performance using synthetic and real data
• [NeurIPS] FreeAnchor Learning to Match Anchors for Visual Object Detection
• [NeurIPS] Cascade RPN Delving into High-Quality Region Proposal Network with Adaptive Convolution
• [ICLR] Why do deep convolutional networks generalize so poorly to small image transformations?
• [ICLR] ImageNet-trained CNNs are biased towards texture: increasing shape bias improves accuracy and robustness
• [ICLR] Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
• [IJCAI] Omnidirectional Scene Text Detection with Sequential-free Box Discretization
• [BMVC] Rethinking Classification and Localization for Cascade R-CNN
• [ICIP] SSSDET: Simple Short and Shallow Network for Resource Efficient Vehicle Detection in Aerial Scenes
• [IEEE Access] A Real-Time Scene Text Detector with Learned Anchor
• [J. Big Data] A survey on Image Data Augmentation for Deep Learning
• [IEEE Trans Geosci Remote Sens] CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery
• [ICTAI] Twin Feature Pyramid Networks for Object Detection
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Double-Head RCNN: Rethinking Classification and Localization for Object Detection
• Learning Data Augmentation Strategies for Object Detection
• A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
• Bag of Freebies for Training Object Detection Neural Networks
• Natural Adversarial Examples
• Needles in Haystacks: On Classifying Tiny Objects in Large Images
• CBNet: A Novel Composite Backbone Network Architecture for Object Detection
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• R3Det Refined Single-Stage Detector with Feature Refinement for Rotating Object
• Deep Learning for 2D and 3D Rotatable Data An Overview of Methods
• Is Sampling Heuristics Necessary in Training Deep Object Detectors
• IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection
• Ship Detection: An Improved YOLOv3 Method
• AugFPN: Improving Multi-scale Feature Learning for Object Detection
• Multi-Scale Attention Network for Crowd Counting
• Revisiting Feature Alignment for One-stage Object Detection
• Consistent Optimization for Single-Shot Object Detection
• Learning from Noisy Anchors for One-stage Object Detection

---

2018

• [CVPR] Cascade R-CNN: Delving into High Quality Object Detection
• [CVPR] Path Aggregation Network for Instance Segmentation
• [CVPR] Scale-Transferable Object Detection
• [CVPR] DOTA: A Large-scale Dataset for Object Detection in Aerial Images
• [CVPR] R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection
• [CVPR] Pseudo Mask Augmented Object Detection
• [CVPR] Single-Shot Object Detection with Enriched Semantics
• [CVPR] Weakly Supervised Instance Segmentation using Class Peak Response
• [CVPR] Single-Shot Refinement Neural Network for Object Detection
• [CVPR] Squeeze-and-Excitation Networks
• [CVPR] An Analysis of Scale Invariance in Object Detection
• [CVPR] Rotation Sensitive Regression for Oriented Scene Text Detection
• [ECCV] DetNet: A Backbone network for Object Detection
• [ECCV] Receptive Field Block Net for Accurate and Fast Object Detection
• [ECCV] Modeling Visual Context is Key to Augmenting Object Detection Datasets
• [ECCV] Learning to Segment via Cut-and-Paste
• [ECCV] Acquisition of Localization Confidence for Accurate Object Detection
• [ECCV] Deep Feature Pyramid Reconfiguration for Object Detection
• [ICLR] Multi-Scale Dense Convolutional Networks for Efficient Prediction
• [ICANN] Further advantages of data augmentation on convolutional neural networks
• [IJCV] What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?
• [WACV] Understanding Convolution for Semantic Segmentation
• [ACCV] Reverse Densely Connected Feature Pyramid Network for Object Detection
• [BMVC] Enhancement of SSD by concatenating feature maps for object detection
• [IJAC] An Overview of Contour Detection Approaches
• [Remote Sens.] Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• [IEEE Trans Multimedia] Arbitrary-oriented scene text detection via rotation proposals
• [J Mach Learn Res] Neural Architecture Search: A Survey
• [VISIGRAPP] Learning Transformation Invariant Representations with Weak Supervision
• MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects
• Data Augmentation by Pairing Samples for Images Classification
• RAM: Residual Attention Module for Single Image Super-Resolution

---

2017

• [AAAI] Weakly Supervised Semantic Segmentation Using Superpixel Pooling Network
• [CVPR] Feature Pyramid Networks for Object Detection
• [CVPR] Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
• [CVPR] Simple Does It: Weakly Supervised Instance and Semantic Segmentation
• [CVPR] Oriented Response Networks
• [ICCV] Single shot scale-invariant face detector
• [ICCV] Focal Loss for Dense Object Detection
• [ICCV] Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection
• [ICCV] Grad-CAM Visual Explanations From Deep Networks via Gradient-Based Localization
• [ICCV] Single Shot Text Detector with Regional Attention
• [ICLR] Dataset Augmentationin In Feature Space
• [ICIP] Rotated region based CNN for ship detection
• [IEEE Acess] Smart Augmentation: Learning an Optimal Data Augmentation Strategy
• [ICPRAM] A High Resolution Optical Satellite Image Dataset for Ship Recognition and Some New Baselines
• FSSD: Feature Fusion Single Shot Multibox Detector
• Improved Regularization of Convolutional Neural Networks with Cutout
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning

---

2016

• [CVPR] Learning Deep Features for Discriminative Localization
• [ECCV] Contextual Priming and Feedback for Faster R-CNN
• [NIPS] R-FCN： Object Detection via Region-based Fully Convolutional Networks
• [DICTA] Understanding data augmentation for classification: when to warp?
• [IEEE Geosci. Remote. Sens. Lett.] Ship Rotated Bounding Box Space for Ship Extraction From High-Resolution Optical Satellite Images With Complex Backgrounds
• Beyond Skip Connections: Top-Down Modulation for Object Detection

---

2015

• [ICDAR] ICDAR 2015 competition on Robust Reading

---

2009

• [ICML] Curriculum learning