SSL

Patterns - Dimitris

review Chowdhury et al.

Contrastive learning

SimCLR — A Simple Framework for Contrastive Learning of Visual Representations ICML 2020 | code

• a two-network training method for visual representations, which maximizes agreement between differently transformed views of the same sample via a contrastive cosine similarity loss in the latent space.

BYOL - Bootstrap Your Own Latent A New Approach to Self-Supervised Learning NeurIPS 2020

• not contrastive, done without negative pairs
• iteratively update the representations, use exponential history mean network as the target

Health domain

Step2Heart

SelfHAR

CLOCS