Generalized Parametric Contrastive Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on pattern analysis and machine intelligence"
DOI: 10.48550/arxiv.2209.12400
Abstract: In this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo) which works well on both imbalanced and balanced data. Based on theoretical analysis, we observe supervised contrastive loss tends to bias on high-frequency classes… read more here.
Keywords: loss; gpaco paco; generalized parametric; analysis ... See more keywords