SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud, CVPR 2021.

The official pytorch implementation of ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias

Early exit ensembles

Repository for the Stanford Knee MRI Multi-Task Evaluation (SKM-TEA) Dataset

The official start-up code for paper "FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark."

Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling

Federated Primal-Dual Algorithm

[CVPR 2021] Contrastive Neural Architecture Search with Neural Architecture Comparators

PyTorch code for ICLR 2021 paper Unbiased Teacher for Semi-Supervised Object Detection

[CVPR 2021] This is the official code for the paper "Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement"

OpenMMLab Model Compression Toolbox and Benchmark.

Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at ICLR 2020

(ICML 2021) Implementation for S2SD - Simultaneous Similarity-based Self-Distillation for Deep Metric Learning. Paper Link: https://arxiv.org/abs/2009.08348

This repository contains the code of the CVPR 2022 paper "Image Segmentation Using Text and Image Prompts".

Google Research

Awesome Incremental Learning

Pytorch implementation of "Large-Scale Meta-Learning with Continual Trajectory Shifting" (ICML 2021)

Code Repository for ICML 2020 accepted paper, named "A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton"

Bilevel Optimization Library in Python for Multi-Task and Meta Learning

Official release of code for "Oops I Took A Gradient: Scalable Sampling for Discrete Distributions"

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

Official PyTorch implementation of "EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization"

A PyTorch implementation of OpenAI's REPTILE algorithm

code for "AttentiveNAS Improving Neural Architecture Search via Attentive Sampling"

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

A PyTorch-based framework for Quantum Classical Simulation, Quantum Machine Learning, Quantum Neural Networks, Parameterized Quantum Circuits with support for easy deployments on real quantum compu…

Representative-Discriminative Open-set Recognition

Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.