Multimodality · 2021
Vision Transformer (An Image is Worth 16x16 Words)
Introduced the Vision Transformer, showing that a plain Transformer applied to fixed-size image patches can match or beat convolutional networks on image classification, removing the assumption that vision required convolution-specific inductive biases.
Editorial record
Plain-language summary
The model splits an image into a grid of small patches (e.g. 16x16 pixels), linearly embeds each patch as if it were a word token, adds position embeddings, and feeds the sequence into a standard Transformer encoder. With no convolutions, it learns spatial structure from data alone, which works well only when pre-trained on very large image datasets. This let the same architecture used for language be reused for vision and scaled up with more data and compute rather than hand-designed vision components.
Knowledge graph
Relationships
Antecedents
Depends onEvidence: Direct
CLIP: Learning Transferable Visual Models from NL Supervision
CLIP uses a ViT image encoder
P-301
Applies toEvidence: Direct
Latent Diffusion (Stable Diffusion) / Diffusion Transformers (DiT)
DiT uses a Transformer denoiser
P-308
Descendants
Applies toEvidence: Direct
Attention Is All You Need
Transformer applied to image patches
P-300
ChallengesEvidence: Strongly supported
AlexNet: ImageNet Classification with Deep CNNs
ViT re-solves vision without convolution
P-300
Source record
Provenance
- Record ID
- P-300
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2010.11929
- arXiv:2010.11929
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.