IndexMapAnti-DoomscrollAbout
See also
ArchitectureImageVideoCross-Modal

Vision Transformer (ViT)

Also known as: ViT · MAE · Masked Autoencoder · NaViT

Plain English

An architecture that applies the Transformer directly to images by slicing a picture into a grid of small square patches and treating each patch like a word in a sentence.

Technical Overview

Proposed by Dosovitskiy et al., ViT flattens P x P image patches into linear token projections with positional embeddings and processes them with standard Transformer encoder blocks. Lacking the built-in translation equivariance of CNNs, ViTs scale strongly with large pretraining datasets or masked patch reconstruction (MAE) and serve as the universal visual backbone for CLIP, DINO, SAM, and VLMs.

Timeline (4)

RSS
  1. 2020

  2. 2021

    Paper

    Kaiming He et al. at Meta AI introduced Masked Autoencoders (MAE), masking 75% of input image patches and applying the ViT encoder only to the visible 25% before a lightweight decoder reconstructs the missing pixels—cutting self-supervised pretraining compute by over 3x.

  3. 2023

  4. 2025

See also (10)

Open full graph
5 more connections