EUVIMEDEUVIMED entdecken
Crossref

Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data

Yang Yang, Nan Jiang, Yi Xu, De-Chuan Zhan

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 8334-8347

DOI: 10.1109/tpami.2024.3403994 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Yang Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: National Key RD Program of China, National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-set Semi-supervised Learning (OSSL) holds a realistic setting that unlabeled data may come from classes unseen in the labeled set, i.e., out-of-distribution (OOD) data, which could cause performance degradation in conventional SSL models. To handle this issue, except for the traditional in-distribution (ID) classifier, some existing OSSL approaches employ an extra OOD detection module to avoid the potential negative impact of the OOD data. Nevertheless, these approaches typically employ the entire set of open-set data during their training process, which may contain data unfriendly to the OSSL task that can negatively influence the model performance. This inspires us to develop a robust open-set data selection strategy for OSSL. Through a theoretical understanding from the perspective of learning theory, we propose Wise Open-set Semi-supervised Learning (WiseOpen), a generic OSSL framework that selectively leverages the open-set data for training the model. By applying a gradient-variance-based selection mechanism, WiseOpen exploits a friendly subset instead of the whole open-set dataset to enhance the model's capability of ID classification. Moreover, to reduce the computational expense, we also propose two practical variants of WiseOpen by adopting low-frequency update and loss-based selection respectively. Extensive experiments demonstrate the effectiveness of WiseOpen in comparison with the state-of-the-art.

Förderung

  • National Key RD Program of China
  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Fundamental Research Funds for the Central University of China
  • Collaborative Innovation Center of Novel Software Technology and Industrialization

Zitieren

APA

Yang, Y., Jiang, N., Xu, Y., & Zhan, D. C. (2024). Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 8334-8347. https://doi.org/10.1109/tpami.2024.3403994

Vancouver

Yang Y, Jiang N, Xu Y, Zhan DC. Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):8334-8347. doi:10.1109/tpami.2024.3403994

BibTeX
@article{Yang2024,
  author = {Yang, Yang and Jiang, Nan and Xu, Yi and Zhan, De-Chuan},
  title = {Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {8334--8347},
  doi = {10.1109/tpami.2024.3403994}
}
Kostenlos starten →