Collapse-Proof Non-Contrastive Self-Supervised Learning

Emanuele Sansone; Tim Lebailly; Tinne Tuytelaars

2025 ICML ICML 2025

Collapse-Proof Non-Contrastive Self-Supervised Learning

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Emanuele Sansone, Tim Lebailly, Tinne Tuytelaars

Topics

Machine Learning > Learning Types > Self-Supervised Learning Deep Learning > Learning Types > Representation Learning

Keywords

inductive bia loss function hyperdimensional computing projector clustered decorrelated

Download PDF