Self-supervised ReLU networks form substantially fewer linear regions than supervised models for comparable accuracy, with contrastive methods rapidly expanding regions and self-distillation consolidating them, enabling early geometric detection of representation collapse.
Self-supervised features improve open-world learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Complexity of Linear Regions in Self-supervised Deep ReLU Networks
Self-supervised ReLU networks form substantially fewer linear regions than supervised models for comparable accuracy, with contrastive methods rapidly expanding regions and self-distillation consolidating them, enabling early geometric detection of representation collapse.