Architectures · advanced · concept 94 of 311 · Updated Nov 4, 2026
Vision Transformer (ViT)
Applying the Transformer architecture to images by splitting them into patches and treating each patch as a token. Showed that attention can match or exceed CNNs for vision tasks at scale.
Top AI contributors on this
- Yann LeCunAMI Labs / NYU
- Andrew NgDeepLearning.AI / AI Fund
- Fei-Fei LiWorld Labs / Stanford University
- Andrej KarpathyAnthropic
- Kaiming HeMIT / Google DeepMind
- Ross GirshickAnthropic
Key terms
Patch embeddingPosition embeddingCLS tokenImage patches
Learn these first
Videos
▶ Attention in transformers, step-by-step | Deep Learning Chapter 6 ↗
3Blue1Brown · YouTube
▶ An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Paper Explained) ↗
Yannic Kilcher · YouTube
Guides and articles
Vision Transformer (ViT) · Hugging Face ↗
Hugging Face
11.8. Transformers for Vision: Dive into Deep Learning 1.0.3 documentation ↗
Dive into Deep Learning
Courses, papers, and more