Alleviating Long-Tailed Image Classification via Dynamical Classwise Splitting

Alleviating Long-Tailed Image Classification via Dynamical Classwise Splitting

With the rapid increase in data scale, real-world datasets tend to exhibit long-tailed class distributions (i.e., a few classes account for most of the data, while most classes contain only a few data points). General solutions typically exploit class rebalancing strategies involving resampling and...

Full description

Bibliographic Details
Main Authors: Ye Yuan, Jiaqi Wang, Xin Xu, Ruoshi Li, Yongtong Zhu, Lihong Wan, Qingdu Li, Na Liu
Format: Article
Language:English
Published: MDPI AG 2023-07-01
Series:Mathematics
Subjects:
deep learning
class-imbalance learning
feature clustering
long-tailed classification
classwise splitting
Online Access:https://www.mdpi.com/2227-7390/11/13/2996

Internet

https://www.mdpi.com/2227-7390/11/13/2996

Similar Items