computer-vision

CNN and Vision Transformer architecture families, surveyed

taught

Recognizing the major CNN architecture families and the Vision Transformer's patch-plus-attention approach at a one-page-each survey level, enough to read an architecture diagram and place it in the landscape without re-deriving it.

Taught in

CNN architecture families, a survey
Computer Vision
Patches, attention, and Vision Transformers
Computer Vision

Requires

cnn-architecture-families recommended
deep-learning ch.16 derives these architecture families in full; this course's own quizzes only require the survey-level version taught locally.
vision-transformer recommended
deep-learning ch.19 derives the Vision Transformer's patch-plus- attention mechanics in full; this course's own quizzes only require the survey-level version taught locally.

Required by

Nothing in the catalog needs this yet.

Local knowledge map

Click to expand

Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.