2 papers
cs.CV2026
OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement
Bin Wang, Fadi Dornaika
Supervised Contrastive Learning (SupCon) has achieved strong performance by explicitly modeling pairwise relationships among samples. However, existing SupCon-based methods suffer…
cs.CV2025
SCS-SupCon: Sigmoid-based Common and Style Supervised Contrastive Learning with Adaptive Decision Boundaries
Bin Wang, Fadi Dornaika
Image classification is hindered by subtle inter-class differences and substantial intra-class variations, which limit the effectiveness of existing contrastive learning methods. S…