CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-10 · 45 (10) · 11521-11539
DOI: 10.1109/tpami.2023.3271451 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-10. Verfasst von Jun Shu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 68-mal zitiert (Crossref) und nennt 110 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Fundo para o Desenvolvimento das Ciências e da Tecnologia.
Abstract (Originalsprache)
Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. Most current methods, however, require to manually pre-specify the weighting schemes relying on the characteristics of the investigated problem and training data. This makes them fairly hard to be generally applied in practical scenarios, due to their significant complexities and inter-class variations of data bias. To address this issue, we propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data. Specifically, by seeing each training class as a separate learning task, our method aims to extract an explicit weighting function with sample loss and task/class feature as input, and sample weight as output, expecting to impose adaptively varying weighting schemes to different sample classes based on their own intrinsic bias characteristics. Extensive experiments substantiate the capability of our method on achieving proper weighting schemes in various data bias cases, like class imbalance, feature-independent and dependent label noises, and more complicated bias scenarios beyond conventional cases. Besides, the task-transferability of the learned weighting scheme is also substantiated, by readily deploying the weighting function learned on relatively smaller-scale CIFAR-10 dataset on much larger-scale full WebVision dataset. The general availability of our method for multiple robust deep learning issues, including partial-label learning, semi-supervised learning and selective classification, has also been validated. Code for reproducing our experiments is available at https://github.com/xjtushujun/CMW-Net.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Fundo para o Desenvolvimento das Ciências e da Tecnologia
Zitieren
APA
Shu, J., Yuan, X., Meng, D., & Xu, Z. (2023). CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10), 11521-11539. https://doi.org/10.1109/tpami.2023.3271451
Vancouver
Shu J, Yuan X, Meng D, Xu Z. CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(10):11521-11539. doi:10.1109/tpami.2023.3271451
BibTeX
@article{Shu2023,
author = {Shu, Jun and Yuan, Xiang and Meng, Deyu and Xu, Zongben},
title = {CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {10},
pages = {11521--11539},
doi = {10.1109/tpami.2023.3271451}
}
EUVIMED