New losses achieve Neural Collapse faster in supervised learning

Researchers have introduced new methods, NTCE and NONL, to improve supervised classification by achieving Neural Collapse (NC) more efficiently. These techniques address limitations in existing paradigms like cross-entropy and supervised contrastive learning. By treating supervised learning as prototype learning on a hypersphere, the new losses enable faster convergence to NC and yield significant improvements in transfer learning and robustness, especially under class imbalance. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces novel losses that accelerate convergence to optimal classification geometry and improve model robustness.

RANK_REASON The cluster contains an academic paper detailing new methods for supervised classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Cross entropy
• ImageNet-1K
• ImageNet-C
• Neural Collapse
• NTCE
• Panagiotis Koromilas
• Supervised contrastive learning

• paper
• model release