Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

The official implementation of ELSA: Enhanced Local Self-Attention for Vision Transformer

VOLO: Vision Outlooker for Visual Recognition

Official code for Conformer: Local Features Coupling Global Representations for Visual Recognition

Official PyTorch implementation of our ECCV 2022 paper "Sliced Recursive Transformer"

Official implementation of PVT series

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

Official repository for the "Big Transfer (BiT): General Visual Representation Learning" paper.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper

Reference implementation for Blueprint Separable Convolutions (CVPR 2020)

Pytorch implementation of "All Tokens Matter: Token Labeling for Training Better Vision Transformers"

Official implementation of the paper Visual Parser: Representing Part-whole Hierarchies with Transformers

Code for the Convolutional Vision Transformer (ConViT)

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

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

A curated list of deep learning image classification papers and codes

Official code Cross-Covariance Image Transformer (XCiT)

The implementation of our paper: Towards Robust Vision Transformer (CVPR2022)

Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones

Implementing Stand-Alone Self-Attention in Vision Models using Pytorch

LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

A Pytorch Implementation of the following paper "Visual Transformers: Token-based Image Representation and Processing for Computer Vision"

Official repository for Big-Little Net

Nearly Perfect & Easily Understandable PyTorch Implementation of SKNet

A PyTorch implementation for PyramidNets (Deep Pyramidal Residual Networks, https://arxiv.org/abs/1610.02915)

Learning Features with Parameter-Free Layers, ICLR 2022