EUVIMEDEUVIMED entdecken
Crossref

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning

Mengmeng Sheng, Zeren Sun, Zhenhuang Cai, Tao Chen, Yichao Zhou, Yazhou Yao

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4820-4828

DOI: 10.1609/aaai.v38i5.28284 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Mengmeng Sheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

There has been significant attention devoted to the effectiveness of various domains, such as semi-supervised learning, contrastive learning, and meta-learning, in enhancing the performance of methods for noisy label learning (NLL) tasks. However, most existing methods still depend on prior assumptions regarding clean samples amidst different sources of noise (e.g., a pre-defined drop rate or a small subset of clean samples). In this paper, we propose a simple yet powerful idea called NPN, which revolutionizes Noisy label learning by integrating Partial label learning (PLL) and Negative learning (NL). Toward this goal, we initially decompose the given label space adaptively into the candidate and complementary labels, thereby establishing the conditions for PLL and NL. We propose two adaptive data-driven paradigms of label disambiguation for PLL: hard disambiguation and soft disambiguation. Furthermore, we generate reliable complementary labels using all non-candidate labels for NL to enhance model robustness through indirect supervision. To maintain label reliability during the later stage of model training, we introduce a consistency regularization term that encourages agreement between the outputs of multiple augmentations. Experiments conducted on both synthetically corrupted and real-world noisy datasets demonstrate the superiority of NPN compared to other state-of-the-art (SOTA) methods. The source code has been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/NPN.

Zitieren

APA

Sheng, M., Sun, Z., Cai, Z., Chen, T., Zhou, Y., & Yao, Y. (2024). Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4820-4828. https://doi.org/10.1609/aaai.v38i5.28284

Vancouver

Sheng M, Sun Z, Cai Z, Chen T, Zhou Y, Yao Y. Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4820-4828. doi:10.1609/aaai.v38i5.28284

BibTeX
@article{Sheng2024,
  author = {Sheng, Mengmeng and Sun, Zeren and Cai, Zhenhuang and Chen, Tao and Zhou, Yichao and Yao, Yazhou},
  title = {Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4820--4828},
  doi = {10.1609/aaai.v38i5.28284}
}
Kostenlos starten →