home.md

@@ -27,6 +27,7 @@ Further Contributors: Mehdi Cherti (MC) (Helmholtz AI HLST, JSC)
 Following directions are currently envisaged, please feel free to add more:
 * Large-Scale Pre-Training and Cross-Domain Transfer (Collaborators: JSC, ...)
   - Auxiliary tasks and losses
+  - Unsupervised, self-supervised pre-training for transfer, e.g. via contrastive losses
   - Generative models for unsupervised pre-training
 * Uncertainty estimation and signaling (Collaborators: JSC, ...)
 * Methods for validation of diagnostics and explainable output (Collaborators: JSC, ...)