What is Vision transformer (ViT)?

Vision transformer (ViT)

Vision transformer (ViT): A model that splits an image into patches, treats them as tokens, and applies transformer attention for image understanding.

Related terms

Computer vision
Diffusion transformer (DiT)
GPT (generative pre-trained transformer)
T5 (Text-to-Text Transfer Transformer)
Transformer
Transformer block
Vision-language model (VLM)
Vision-language-action model (VLA)

Browse the full glossary →