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...
Main Authors: | , , , , , |
---|---|
Andre forfattere: | |
Format: | Journal Article |
Sprog: | English |
Udgivet: |
2023
|
Fag: | |
Online adgang: | https://hdl.handle.net/10356/172214 |