Paper Info
An image is worth 16x16 words: Transformers for image recognition at scale
A Dosovitskiy, L Beyer, A Kolesnikov, D Weissenborn, X Zhai, T Unterthiner, M Dehghani, M Minderer, G Heigold, S Gelly, o others
arXiv preprint arXiv:2010.11929, 2020.
Reviews
From
yassendobrev, rated
5/5.
Nov. 15, 2021.
A very interesting paper comparing Transformers and CNNs for image recognition.
An image is worth 16x16 words: Transformers for image recognition at scale
A Dosovitskiy, L Beyer, A Kolesnikov, D Weissenborn, X Zhai, T Unterthiner, M Dehghani, M Minderer, G Heigold, S Gelly, o others
arXiv preprint arXiv:2010.11929, 2020.
Reviews
From
yassendobrev, rated
5/5.
Nov. 15, 2021.
A very interesting paper comparing Transformers and CNNs for image recognition.