google-research/vision_transformerGitHub
calls T2T-ViT “choose for a tokens-to-token ViT variant that trains from scratch better than plain ViT; PyTorch but older.”
12.7kJupyter Notebookactive
T2T-ViT is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
These projects were analysed and named T2T-ViT among their alternatives. The relationship is not symmetric — how T2T-ViT rates them is a separate judgement, made when T2T-ViT is analysed in its own right.
calls T2T-ViT “choose for a tokens-to-token ViT variant that trains from scratch better than plain ViT; PyTorch but older.”