Papers

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

• Original paper introducing Vision Transformers

Videos

Vision Transformer Paper Walkthrough

• By Yannic Kilcher

Vision Transformer (ViT)

• Overview by AI Bites

Vision Transformer in Pytorch

• A video walking through implementing a Vision Transformer

Code Examples

Vision Transformer Github Code

• Code released by the Google Research team with the paper

Vision Transformer - Pytorch

• Another implementation of ViT with good documentation

Vision Transformer

• An easy-to-follow implementation in pytorch

Vision Transformer Keras Tutorial

• A simple Keras version of ViT