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

v1v2v3 (latest)

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

28 January 2021

Weihao Yu

Francis E. H. Tay

ArXiv (abs)PDF HTML Github (1188★)

Papers citing "Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet"

0 / 73 papers shown

Title
No papers