Metraipolis › archive › dc_75ee1854015a

Vision transformer — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/Vision_transformer
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-06T13:39:48.605Z
SHA-256 of the archived text
0cd6502b8519dcd773b8799b619c962ac54ad5e0550b1ae6c77e60ee03d240c7
Stable URL of this page
https://metraipolis.com/documento/dc_75ee1854015a

How to cite

Vision transformer — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Vision_transformer (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_75ee1854015a (Metraipolis archive dc_75ee1854015a, sha256 0cd6502b8519dcd773b8799b619c962ac54ad5e0550b1ae6c77e60ee03d240c7)
BibTeX
@misc{dc75ee1854015a,
  title = {Vision transformer — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/Vision_transformer},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_75ee1854015a; sha256 0cd6502b8519dcd773b8799b619c962ac54ad5e0550b1ae6c77e60ee03d240c7},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Vision_transformer. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A vision transformer (ViT) is a transformer designed for computer vision. A ViT decomposes an input image into a series of patches (rather than text into tokens), serializes each patch into a vector, and maps it to a smaller dimension with a single matrix multiplication. These vector embeddings are then processed by a transformer encoder as if they were token embeddings. ViTs were designed as alternatives to convolutional neural networks (CNNs) in computer vision applications. They have different inductive biases, training stability, and data efficiency. Compared to CNNs, ViTs are less data efficient, but have higher capacity. Some of the largest modern computer vision models are ViTs, such as one with 22B parameters. Subsequent to its publication, many variants were proposed, with hybrid architectures with both features of ViTs and CNNs. ViTs have found application in image recognition, image segmentation, weather prediction, and autonomous driving.

Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «computer vision»).
Fonte: Wikipedia in inglese, voce «Vision transformer» — https://en.wikipedia.org/wiki/Vision_transformer
Wikidata Q107675654: «machine learning algorithm for vision processing» (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q107675654
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Vision_transformer?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1374802351, consultata il 2026-10-06T11:56:22.068Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: a64f4168f1658a4e36d235fee31ee99614dd615445595eb08241b1ee497a1697