Skip to content

Latest commit

 

History

History
7 lines (4 loc) · 327 Bytes

210402 LeViT.md

File metadata and controls

7 lines (4 loc) · 327 Bytes

https://arxiv.org/abs/2104.01136

LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference (Ben Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jégou, Matthijs Douze)

비전 트랜스포머 + 다운샘플링 한 편 더! batch norm을 사용한 것도 특징.

#vision_transformer