Saral Shiksha Yojna
Courses/Computer Vision

Computer Vision

CSE471
Prof. Makarand Tapaswi + Prof. Charu Sharma•Spring 2025-26•4 credits
Revision Notes/Unit 8 — SSL: Contrastive (SimCLR, MoCo, BYOL, CLIP)

Unit 8 — SSL: Contrastive (SimCLR, MoCo, BYOL, CLIP)

Self-supervised learning derives labels from the data itself. Contrastive methods pull positive pairs together and push negatives apart; CLIP scales this to image-text. Includes BYOL's 'no negatives' trick.

Contrastive SSL — SimCLR / MoCo / BYOL / CLIP

14 min

Self-supervised learning invents the supervision signal: 'this random crop and that random crop of the same image should look similar; everything else in the batch should look different.' That's the entirety of SimCLR. Variants then attack the dependency on huge batches.