Saral Shiksha Yojna
Courses/Computer Vision

Computer Vision

CSE471
Prof. Makarand Tapaswi + Prof. Charu Sharma•Spring 2025-26•4 credits
Revision Notes/Unit 9 — SSL: DINO, MAE, JEPA

Unit 9 — SSL: DINO, MAE, JEPA

Self-distillation without labels (DINO), masked reconstruction in pixel space (MAE), and prediction in representation space (JEPA). DINO's anti-collapse tricks are heavily tested.

DINO, MAE, JEPA — Modern SSL Beyond Contrastive

13 min

DINO trains a student to match an EMA teacher's output distribution. MAE masks 75% of patches and reconstructs pixels. JEPA predicts target REPRESENTATIONS instead of pixels. All three avoid negatives entirely.