Self-Supervision & Contrastive Frameworks - A Vision-Based Review

Self-Supervision & Contrastive Frameworks - A Vision-Based Review

Stanford MedAI via YouTube Direct link

DINO: Main Principle

30 of 32

30 of 32

DINO: Main Principle

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Self-Supervision & Contrastive Frameworks - A Vision-Based Review

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 SS Learning: Invariant Representations
  3. 3 Pre-text Tasks: A Deeper Dive
  4. 4 Contrastive Learning: Entity Discrimination
  5. 5 Contrastive Learning: Problem
  6. 6 SimCLR: Simple Contrastive Learning Representatio
  7. 7 SimCLR: Architecture
  8. 8 SimCLR: Loss Function
  9. 9 SimCLR: Findings
  10. 10 MoCo V2: Momentum Contrast
  11. 11 MoCo V2: Architecture
  12. 12 MoCo V2: Main Principle
  13. 13 MoCoV2: Loss Function
  14. 14 MoCo V2: Findings
  15. 15 BYOL: Bootstrap Your Own Latent
  16. 16 BYOL: Architecture
  17. 17 BYOL: Main Principle
  18. 18 BYOL: Findings
  19. 19 SWAV: Swapping Assignments between Views
  20. 20 SWAV: Architecture
  21. 21 SWAV: Loss Function
  22. 22 SWAV: Main Principle
  23. 23 SWAV: Multi-crop
  24. 24 SWAV: Additional Findings
  25. 25 DINO: Self-Distillation with NO labels
  26. 26 DINO: Attention-Maps
  27. 27 VIT (Vision Transformer): Architecture
  28. 28 DINO: Architecture
  29. 29 DINO: Loss Function
  30. 30 DINO: Main Principle
  31. 31 DINO: Multi-crop
  32. 32 DINO: Additional Findings Compute

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.