Pulls two augmented views of one image together in embedding space and pushes other images apart. Learns without labels, and the augmentations quietly decide what the features will ignore.
supersedescorrects · extends
classifiesspecializes · part-of
substitutes forapproximates · alternative-to
depends onrequires · validates
Colour is the family; a dashed line is the second member of it.
Drag to pan · scroll to zoom · click a node to open it
Referenced by
correctsBYOL fixes a defect in thisnegative pairs turn out not to be necessary
specializesCLIP is a specific case of thisthe positive pair is an image and its own caption
correctsMomentum Contrast fixes a defect in thisnegatives need a batch bigger than memory allows
References
A Simple Framework for Contrastive Learning of Visual Representations — Chen, Kornblith, Norouzi, Hinton — 2020 · link