Vision

9 concepts, 9 reviewed and merged.

Architecture

Feature PyramidThe same object is a hundred pixels across in one photograph and eight in the next, and a detector with one fixed…verified

Dense Prediction

Instance SegmentationSemantic segmentation says these pixels are all 'person'.verified
Promptable SegmentationRather than training a model to segment a fixed list of categories, train one to segment whatever a person points at.verified
Semantic SegmentationLabel every pixel with what it belongs to — road, building, sky — without distinguishing one car from the car parked…verified

Foundations

Motion

Optical FlowFor every pixel in one frame, where did it go in the next? The answer is a dense field of little arrows, and it is…verified

Recognition

Object DetectionClassification asks what is in the picture; detection asks what is in it and where, which turns one answer into a…verified

Video

Video UnderstandingA video is a stack of images, but treating it as one wastes almost everything: consecutive frames are nearly…verified