Self-supervised Learning: Theories (Part 2)

#Self-supervised Learning

We will dive deep into Section 6 of the paper arXiv:2006.08218. Here are a few topics to be explored.

  • InfoGAN objective;
  • Positive and negative samples in loss function (InfoNCE);
  • Uniformity in constrastive loss;
  • JS-divergence.

Published: by ;

Current Ref:

  • cpe/20.self-supervised-learning-theories-2.md