ConceptAI & ML
Vision transformer
A vision transformer is an architecture that applies the transformer encoder to image patches for image recognition tasks.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
Steven Feng
Drew Jaegle
A transformer architecture applied to images that uses an initial 2D convolution to reduce an image to a set of patch tokens.Lucas Beyer
A model that applies the transformer architecture directly to image patches for computer vision tasks.
Lectures that assume it
1Connections
15The lectures that define it or assume it, and the concepts next to it.