.png){kind=icon}
Return
Weight-guided class complementing for long-tailed image recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109374.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Real-world data are often long-tailed distributed and have plenty classes. This characteristic leads to a significant performance drop for various models. One reason behind that is the gradient shift caused by unsampled classes in each training iteration. In this paper, we propose a Weight-Guided Class Complementing framework to address this issue. Specifically, this framework first complements the un-sampled classes in each training iteration by using a dynamic updated data slot. Then, considering the over-fitting issue caused by class complementing, we utilize the classifier weights as learned knowledge and encourage the model to discover more class specific characteristics. Finally, we design a weight refin-ing scheme to deal with the long-tailed bias existing in classifier weights. Experimental results show that our framework can be implemented upon different existing approaches effectively, achieving consistent improvements on various benchmarks with new state-of-the-art performances. Codes will be released.(c) 2023 Elsevier Ltd. All rights reserved.
Keywords:
Image recognition
Long-tailed distribution
Gradient shift
Weight-guided method
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
Cited Papers
Arsenic removal from aqueous solutions by adsorption using novel MIL-53(Fe) as a highly efficient adsorbent.png)
RSC Advances
RSC AdvancesIF0
PREAI
ShareSaveGeometric imbalanced deep learning with feature scaling and boundary sample miningPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSaveShareSaveDeep super-class learning for long-tail distributed image classificationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave no more
no more