Vision Transformer
Vision Transformer applies a Transformer encoder to sequences of image patches. The paper shows that attention-based image models can compete strongly when pretrained at sufficient scale.
Overview. Vision Transformer applies a Transformer encoder to sequences of image patches.
Context. The paper shows that attention-based image models can compete strongly when pretrained at sufficient scale.
Claims and evidence
Claim ledger, 2Vision Transformer applies a Transformer encoder to sequences of image patches.
The paper shows that attention-based image models can compete strongly when pretrained at sufficient scale.