EUVIMEDEUVIMED entdecken
Crossref

Multi-Classifier Adversarial Optimization for Active Learning

Lin Geng, Ningzhong Liu, Jie Qin

Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (6) · 7687-7695

DOI: 10.1609/aaai.v37i6.25932 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Lin Geng und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Active learning (AL) aims to find a better trade-off between labeling costs and model performance by consciously selecting more informative samples to label. Recently, adversarial approaches have emerged as effective solutions. Most of them leverage generative adversarial networks to align feature distributions of labeled and unlabeled data, upon which discriminators are trained to better distinguish between them. However, these methods fail to consider the relationship between unlabeled samples and decision boundaries, and their training processes are often complex and unstable. To this end, this paper proposes a novel adversarial AL method, namely multi-classifier adversarial optimization for active learning (MAOAL). MAOAL employs task-specific decision boundaries for data alignment while selecting the most informative samples to label. To fulfill this, we introduce a novel classifier class confusion (C3) metric, which represents the classifier discrepancy as the inter-class correlation of classifier outputs. Without any additional hyper-parameters, the C3 metric further reduces the negative impacts of ambiguous samples in the process of distribution alignment and sample selection. More concretely, the network is trained adversarially by adding two auxiliary classifiers, reducing the distribution bias of labeled and unlabeled samples by minimizing the C3 loss between classifiers, while learning tighter decision boundaries and highlighting hard samples by maximizing the C3 loss. Finally, the unlabeled samples with the highest C3 loss are selected to label. Extensive experiments demonstrate the superiority of our approach over state-of-the-art AL methods in terms of image classification and object detection.

Zitieren

APA

Geng, L., Liu, N., & Qin, J. (2023). Multi-Classifier Adversarial Optimization for Active Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 37(6), 7687-7695. https://doi.org/10.1609/aaai.v37i6.25932

Vancouver

Geng L, Liu N, Qin J. Multi-Classifier Adversarial Optimization for Active Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(6):7687-7695. doi:10.1609/aaai.v37i6.25932

BibTeX
@article{Geng2023,
  author = {Geng, Lin and Liu, Ningzhong and Qin, Jie},
  title = {Multi-Classifier Adversarial Optimization for Active Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2023},
  volume = {37},
  number = {6},
  pages = {7687--7695},
  doi = {10.1609/aaai.v37i6.25932}
}
Kostenlos starten →