OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement
Researchers have developed a new framework called OSCS-SupCon to improve supervised contrastive learning. This method addresses limitations in existing approaches, such as negative-sample dilution and feature entanglement, by introducing a sigmoid-based contrastive loss and enforcing orthogonality between common and style feature subspaces. Experiments show OSCS-SupCon outperforms state-of-the-art methods, achieving a notable accuracy improvement on the CUB200-2011 dataset. AI
IMPACT Introduces a novel method for feature disentanglement, potentially improving performance in various computer vision tasks.