Improving tail-class representation with centroid contrastive learning

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...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors: Tiong, Anthony Meng Huat, Li, Junnan, Lin, Guosheng, Li, Boyang, Xiong, Caiming, Hoi, Steven C. H.
Andre forfattere: School of Computer Science and Engineering
Format: Journal Article
Sprog:English
Udgivet: 2023
Fag:
Online adgang:https://hdl.handle.net/10356/172214