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

Refine high-quality datasets and visual AI models

code for [ECCV 2022 paper] Contributions of Shape, Texture, and Color in Visual Recognition

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

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

The Official PyTorch Implementation of DiscoBox.

NP DRAW paper released code

MoEx (Moment Exchange)

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

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

JHU Thesis Template

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

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

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

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

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

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

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

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

A deck tracker and deck manager for Hearthstone on Windows

Official DeiT repository

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

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