Imbalanced Label Distribution Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (9) · 11336-11344
DOI: 10.1609/aaai.v37i9.26341 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Xingyu Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref).
Abstract (Originalsprache)
Label distribution covers a certain number of labels, representing the degree to which each label describes an instance. The learning process on the instances labeled by label distributions is called Label Distribution Learning (LDL). Although LDL has been applied successfully to many practical applications, one problem with existing LDL methods is that they are limited to data with balanced label information. However, annotation information in real-world data often exhibits imbalanced distributions, which significantly degrades the performance of existing methods. In this paper, we investigate the Imbalanced Label Distribution Learning (ILDL) problem. To handle this challenging problem, we delve into the characteristics of ILDL and empirically find that the representation distribution shift is the underlying reason for the performance degradation of existing methods. Inspired by this finding, we present a novel method named Representation Distribution Alignment (RDA). RDA aligns the distributions of feature representations and label representations to alleviate the impact of the distribution gap between the training set and the test set caused by the imbalance issue. Extensive experiments verify the superior performance of RDA. Our work fills the gap in benchmarks and techniques for practical ILDL problems.
Zitieren
APA
Zhao, X., An, Y., Xu, N., Wang, J., & Geng, X. (2023). Imbalanced Label Distribution Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 37(9), 11336-11344. https://doi.org/10.1609/aaai.v37i9.26341
Vancouver
Zhao X, An Y, Xu N, Wang J, Geng X. Imbalanced Label Distribution Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(9):11336-11344. doi:10.1609/aaai.v37i9.26341
BibTeX
@article{Zhao2023,
author = {Zhao, Xingyu and An, Yuexuan and Xu, Ning and Wang, Jing and Geng, Xin},
title = {Imbalanced Label Distribution Learning},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {9},
pages = {11336--11344},
doi = {10.1609/aaai.v37i9.26341}
}
EUVIMED