ViT

Overview

ViT splits an image into fixed-size patches, embeds each as a token, and processes the sequence with an ordinary transformer. It solves the problem that convolutional architectures bake in assumptions about locality that a large enough model does not need. It exists because it showed that the architecture which won in language transfers to vision once there is enough data, which removed the main reason the two fields had different toolkits.

Technology Graph

How ViT connects to the rest of the stack.

Alternatives

• CNN architecture

  An alternative to ViT · source

Comparisons

Side-by-side breakdowns with the alternatives above.

• CNN vs ViT