EUVIMEDEUVIMED entdecken
Crossref

PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning

Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, Junbo Zhao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-05 · 46 (5) · 3183-3198

DOI: 10.1109/tpami.2023.3342650 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-05. Verfasst von Haobo Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: NSFC, AFOSR Young Investigator Program, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set with the ground-truth label included. However, in a more practical but challenging scenario, the annotator may miss the ground-truth and provide a wrong candidate set, which is known as the noisy PLL problem. To remedy this problem, we propose the PiCO+ framework that simultaneously disambiguates the candidate sets and mitigates label noise. Core to PiCO+, we develop a novel label disambiguation algorithm PiCO that consists of a contrastive learning module along with a novel class prototype-based disambiguation method. Theoretically, we show that these two components are mutually beneficial, and can be rigorously justified from an expectation-maximization (EM) algorithm perspective. To handle label noise, we extend PiCO to PiCO+, which further performs distance-based clean sample selection, and learns robust classifiers by a semi-supervised contrastive learning algorithm. Beyond this, we further investigate the robustness of PiCO+ in the context of out-of-distribution noise and incorporate a novel energy-based rejection method for improved robustness. Extensive experiments demonstrate that our proposed methods significantly outperform the current state-of-the-art approaches in standard and noisy PLL tasks and even achieve comparable results to fully supervised learning.

Förderung

  • NSFC
  • AFOSR Young Investigator Program
  • National Science Foundation
  • Office of Naval Research
  • Philanthropic Fund from SFF
  • Google
  • Meta
  • National Natural Science Foundation of China

Zitieren

APA

Wang, H., Xiao, R., Li, Y., Feng, L., Niu, G., Chen, G., & Zhao, J. (2024). PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 3183-3198. https://doi.org/10.1109/tpami.2023.3342650

Vancouver

Wang H, Xiao R, Li Y, Feng L, Niu G, Chen G, et al. PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(5):3183-3198. doi:10.1109/tpami.2023.3342650

BibTeX
@article{Wang2024,
  author = {Wang, Haobo and Xiao, Ruixuan and Li, Yixuan and Feng, Lei and Niu, Gang and Chen, Gang and Zhao, Junbo},
  title = {PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {5},
  pages = {3183--3198},
  doi = {10.1109/tpami.2023.3342650}
}
Kostenlos starten →