Week 12: Self-Supervised and Vision-Language Models

Contents

Week 12: Self-Supervised and Vision-Language Models#

Contrastive and self-supervised learning, CLIP and its successors, and the path from vision-language models to multimodal LLMs.

Lectures#

  1. Contrastive Learning, Part 1

  2. Contrastive Learning, Part 2

  3. Self-Supervised Learning: SimCLR

  4. Vision-Language Models: Introduction and History

  5. CLIP

  6. Beyond CLIP: BLIP, BLIP-2 and CoCa

  7. From VLMs to Multimodal LLMs

  8. Course Conclusion

Contents