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...
Saved in:
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: | |
在線閱讀: | https://hdl.handle.net/10356/172214 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Automatic, high accuracy prediction of reopened bugs
由: Xia, Xin, et al.
出版: (2015) -
DML-PL: deep metric learning based pseudo-labeling framework for class imbalanced semi-supervised learning
由: Yan, Mi, et al.
出版: (2023) -
Conditional contrastive domain generalization for fault diagnosis
由: Ragab, Mohamed, et al.
出版: (2022) -
Multi-level transitional contrast learning for personalized image aesthetics assessment
由: Yang, Zhichao, et al.
出版: (2023) -
MITIGATING FEATURE SUPPRESSION IN CONTRASTIVE LEARNING
由: ZHANG JIHAI
出版: (2024)