Attack Can Benefit: An Adversarial Approach to Recognizing Facial Expressions under Noisy Annotations
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (3) · 3660-3668
DOI: 10.1609/aaai.v37i3.25477 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Jiawen Zheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref).
Abstract (Originalsprache)
The real-world Facial Expression Recognition (FER) datasets usually exhibit complex scenarios with coupled noise annotations and imbalanced classes distribution, which undoubtedly impede the development of FER methods. To address the aforementioned issues, in this paper, we propose a novel and flexible method to spot noisy labels by leveraging adversarial attack, termed as Geometry Aware Adversarial Vulnerability Estimation (GAAVE). Different from existing state-of-the-art methods of noisy label learning (NLL), our method has no reliance on additional information and is thus easy to generalize to the large-scale real-world FER datasets. Besides, the combination of Dataset Splitting module and Subset Refactoring module mitigates the impact of class imbalance, and the Self-Annotator module facilitates the sufficient use of all training data. Extensive experiments on RAF-DB, FERPlus, AffectNet, and CIFAR-10 datasets validate the effectiveness of our method. The stabilized enhancement based on different methods demonstrates the flexibility of our proposed GAAVE.
Zitieren
APA
Zheng, J., Li, B., Zhang, S., Wu, S., Cao, L., & Ding, S. (2023). Attack Can Benefit: An Adversarial Approach to Recognizing Facial Expressions under Noisy Annotations. Proceedings of the AAAI Conference on Artificial Intelligence, 37(3), 3660-3668. https://doi.org/10.1609/aaai.v37i3.25477
Vancouver
Zheng J, Li B, Zhang S, Wu S, Cao L, Ding S. Attack Can Benefit: An Adversarial Approach to Recognizing Facial Expressions under Noisy Annotations. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(3):3660-3668. doi:10.1609/aaai.v37i3.25477
BibTeX
@article{Zheng2023,
author = {Zheng, Jiawen and Li, Bo and Zhang, Shengchuan and Wu, Shuang and Cao, Liujuan and Ding, Shouhong},
title = {Attack Can Benefit: An Adversarial Approach to Recognizing Facial Expressions under Noisy Annotations},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {3},
pages = {3660--3668},
doi = {10.1609/aaai.v37i3.25477}
}
EUVIMED