Yingwei Li

focoos. 🚀 Lightning-fast computer vision models. Fine-tune SOTA models with just a few lines of code. Ready for cloud ☁️ and edge 📱 deployment.

fiftyone. Refine high-quality datasets and visual AI models

Humanoid-Vision-Engine. code for [ECCV 2022 paper] Contributions of Shape, Texture, and Color in Visual Recognition

video-semisup. Learning from Temporal Gradient for Semi-supervised Action Recognition (CVPR 2022)

ViTs-vs-CNNs. [NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)

MVP. Python

DiscoBox. The Official PyTorch Implementation of DiscoBox.

NPDRAW. NP DRAW paper released code

MoEx. MoEx (Moment Exchange)

performer-pytorch. An implementation of Performer, a linear attention-based transformer, in Pytorch

Nystromformer. Python

Cross-Modal-Center-Loss. Cross-Modal Center Loss for 3D Cross-Modal Retrieval (CVPR2021)

jhu-thesis-template. JHU Thesis Template

UniDet. Object detection on multiple datasets with an automatically learned unified label space.

DALL-E. PyTorch package for the discrete VAE used for DALL·E.

TransUNet. This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.

NeMo. The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

MOS_Meticulous-Object-Segmentation.

T2T-ViT. ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

DeepRobust. A pytorch adversarial library for attack and defense methods on images and graphs

Deformable-DETR. Deformable DETR: Deformable Transformers for End-to-End Object Detection.

subway-data-processing. Jupyter Notebook

pcl.pytorch. PyTorch codes for our papers "Multiple Instance Detection Network with Online Instance Classifier Refinement" and "PCL: Proposal Cluster Learning for Weakly Supervised Object Detection".

Hearthstone-Deck-Tracker. A deck tracker and deck manager for Hearthstone on Windows

compatible-product. HTML

deit. Official DeiT repository

MGMatting. This repository includes the official project of Mask Guided (MG) Matting, presented in our paper: Mask Guided Matting via Progressive Refinement Network

CAKES. This repository contains the code for our AAAI2021 paper CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks.

ViP-DeepLab. Python

RobustPointSet. Python

DS-Net. [CVPR 2021/TPAMI 2023] Rank 1st in the public leaderboard of SemanticKITTI Panoptic Segmentation (2020-11-16)

BNET. Batch Normalization with Enhanced Linear Transformation

Cylinder3D. Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)

stereo-transformer. Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers. (ICCV 2021 Oral)

ares. A Python library for adversarial machine learning focusing on benchmarking adversarial robustness.

InfoDrop. Code for our paper "Informative Dropout for Robust Representation Learning: A Shape-bias Perspective" (ICML 2020)

meta-dataset. A dataset of datasets for learning to learn from few examples

Unsupervised-Visual-Recognition-by-Solving-Arbitrary-Puzzles. Tensorflow implementation for this paper.

occlusion_person. A dataset for multiview 3D human pose estimation with detailed occlusion labels, powered by UnrealCV

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

unreal-stereo-evaluation. UnrealStereo: Controlling Hazardous Factors to Analyze Stereo Vision

Adversarial-Distributional-Training. Adversarial Distributional Training (NeurIPS 2020)

Seg-Uncertainty. IJCAI2020 & IJCV2021 :city_sunrise: Unsupervised Scene Adaptation with Memory Regularization in vivo

SynthCP. Offical code base for the ECCV oral paper "Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation"

PsTuts. PyTorch code for the CVPR'2020 paper "Screencast Tutorial Video Understanding"

Bag-of-Tricks-for-AT. Empirical tricks for training robust models (ICLR 2021)

Geo-CNN. Python

ShapeTextureDebiasedTraining. Code and models for the paper Shape-Texture Debiased Neural Network Training (ICLR 2021)

imagenet-r. ImageNet-R(endition) and DeepAugment (ICCV 2021)

SmoothAdversarialTraining. Smooth Adversarial Training

pytorch-classification-advprop. Python

single-path-nas. Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

lingvo. Lingvo

H3DNet. Python

Regional-Homogeneity. Source code for Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses (ECCV 2020)

PatchAttack. PatchAttack (ECCV 2020)

DetectoRS. DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

DMM_Net. Differentiable Mask-Matching Network for Video Object Segmentation (ICCV 2019)

DeepLabv3.pytorch. PyTorch implementation of DeepLabv3

AutoNL. Code for AutoNL on ImageNet (CVPR2020)

Trained-Rank-Pruning. Pytorch implementation of TRP

yet_another_mobilenet_series. Yet Another Pytorch Distributed MobileNetV2-based Networks Implementation

UPC-tf. Python

mn-torch. Mode normalization (ICLR 2019).

CenterTrack. Simultaneous object detection and tracking using center points.

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

SAKE. Python

VSRN. PyTorch code for ICCV'19 paper "Visual Semantic Reasoning for Image-Text Matching"

Self-Similarity-Grouping. Self-similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-identification (ICCV 2019, Oral)

natural-adv-examples. A Harder ImageNet Test Set (CVPR 2021)

Awesome-AutoML-and-Lightweight-Models. A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.

Translation-Invariant-Attacks. The translation-invariant adversarial attack method to improve the transferability of adversarial examples.

minimalRL. Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

CenterNet. Object detection, 3D detection, and pose estimation using center point detection:

AlphaX-NASBench101. Neural Architecture Search using Deep Neural Network and Monte Carlo Tree Search

fdu-gradhotpot. Hotpot计划是复旦留学申请数据开源计划的代称，旨在为复旦学弟学妹无偿分享留学申请经验、暑研动态、海外生活/工作等一切相关信息。

proxylessnas. [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

WeightStandardization. Standardizing weights to accelerate micro-batch training

Adversarial_Metric_Attack. The code of "Adversarial Metric Attack for Person Re-identification"

ImageNet-Adversarial-Training. ImageNet classifier with state-of-the-art adversarial robustness

simpledet. A Simple and Versatile Framework for Object Detection and Instance Recognition

smallhardface. Source code for Robust Face Detection via Learning Small Faces on Hard Images

ExtremeNet. Bottom-up Object Detection by Grouping Extreme and Center Points

oicr. Caffe codes for our papers "Multiple Instance Detection Network with Online Instance Classifier Refinement" and "PCL: Proposal Cluster Learning for Weakly Supervised Object Detection".

pancreas-seg. Pancreas Segmentation in Abdominal CT Scans with Convolutional Neural Network

AwesomeTools. Awesome tools make life better.

DI-2-FGSM. Improving Transferability of Adversarial Examples with Input Diversity

NIPS2017_adv_challenge_defense. Mitigating Adversarial Effects Through Randomization

DAG. Adversarial Examples for Semantic Segmentation and Object Detection

AdversarialNetsPapers. Awesome paper list with code about generative adversarial nets

TuSimple-DUC. Understanding Convolution for Semantic Segmentation

patternSpeechRecognition. A MATLAB simulation of speech recognition based on pattern analysis, Mel Frequency Cepstral Coefficients as extracted feature and Dynamc Time Warping as similarity measurement.

YuxinMap. YuxinMap - Data Structure Project

VerticalShowcaseSlider. A tutorial on how to create a responsive vertical fullscreen slider that moves its sections in opposite directions. We'll be using jQuery, CSS Transitions and media queries to make the layout adaptive.

frontend-guidelines. Some HTML, CSS and JS best practices.