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.
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Imbalanced Learning; Contrastive Learning
• Online Access: https://hdl.handle.net/10356/172214
• Institution: Nanyang Technological University

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...