OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement 事件

OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement arXiv:2606.11233v1 Announce Type: new Abstract: Supervised Contrastive Learning (SupCon) has achieved strong performance by explicitly modeling pairwise relationships among samples. However, existing SupCon-based methods suffer from two key limitations: negative-sample dilution induced by the standard InfoNCE loss, and feature-space entanglement caused by the lack of explici