Improving tail-class representation with centroid contrastive learning

• Main Authors: Tiong, Anthony Meng Huat, Li, Junnan, Lin, Guosheng, Li, Boyang, Xiong, Caiming, Hoi, Steven C. H.
• 其他作者: School of Computer Science and Engineering
• 格式: Article
• 語言: English
• 出版: 2023
• 主題: Engineering::Computer science and engineering; Imbalanced Learning; Contrastive Learning
• 在線閱讀: https://hdl.handle.net/10356/172214

In vision domain, large-scale natural datasets typically exhibit long-tailed distribution which has large class imbalance between head and tail classes. This distribution poses difficulty in learning good representations for tail classes. Recent developments have shown good long-tailed model can be...