Transformers in Vision

Architectures

ViT

Swin

DEIT

GitHub - facebookresearch/deit: Official DeiT repository

Training

Small Data

https://github.com/hananshafi/vits-for-small-scale-datasets

Detection

VitDet

detectron2/projects/ViTDet at main · facebookresearch/detectron2 · GitHub

Links

Code

• GitHub - lucidrains/vit-pytorch: Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Videos

• Transformers in Vision: From Zero to Hero (2021)
• Workshop on Attention and Transformers in Vision | CVPR 2022
• Beyond Convolutional Neural Networks | CVPR 2022 Tutorial

Papers

• Efficient Transformers: A Survey
• GitHub - Sense-X/SiT: Official implementation of “Self-slimmed Vision Transformer” (ECCV2022)