Courses/Computer Vision

Computer Vision

CSE471

Prof. Makarand Tapaswi + Prof. Charu Sharma•Spring 2025-26•4 credits

Revision Notes/Unit 7 — Vision Transformers (ViT)

Unit 7 — Vision Transformers (ViT)

Image-as-tokens: patchify, project, prepend a [CLS], add positional embeddings, run a Transformer encoder, classify. ViT scales beautifully but needs massive data; Swin localises attention for efficiency.

ViT Pipeline, Scaling, and Swin

13 min

Feeding 50 K raw pixels into self-attention is infeasible (O(n²)). ViT solves this by treating non-overlapping 16×16 patches as 'words' — for a 224² image that's 14×14 = 196 tokens, well within Transformer reach.