EUVIMEDEUVIMED entdecken
Crossref

Trusted Multi-View Learning Under Noisy Supervision

Yilin Zhang, Cai Xu, Han Jiang, Ziyu Guan, Wei Zhao, Xiaofei He, Murat Sensoy

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-09 · 48 (9) · 10827-10843

DOI: 10.1109/tpami.2026.3690466 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-09. Verfasst von Yilin Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Projects of Shaanxi Province, Xidian University Specially Funded Project for Interdisciplinary Exploration.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-view learning methods often focus on improving decision accuracy while neglecting the decision uncertainty, which significantly restricts their applications in safety-critical scenarios. To address this, trusted multi-view learning methods estimate prediction uncertainties by learning class distributions from each instance. However, these methods heavily rely on high-quality ground-truth labels. This motivates us to delve into a new problem: how to develop a reliable multi-view learning model under the guidance of noisy labels? We propose the Trusted Multi-view Noise Refining (TMNR) method to address this challenge by modeling label noise arising from low-quality data features and easily-confused classes. TMNR employs evidential deep neural networks to construct view-specific opinions that capture both beliefs and uncertainty. These opinions are then transformed through noise correlation matrices to align with the noisy supervision, where matrix elements are constrained by sample uncertainty to reflect label reliability. Furthermore, considering the challenge of jointly optimizing the evidence network and noise correlation matrices under noisy supervision, we further propose Trusted Multi-view Noise Re-Refining (TMNR$^{\mathbf{2}}$2), which disentangles this complex co-training problem by establishing different training objectives for distinct modules. TMNR$^{\mathbf{2}}$2 identifies potentially mislabeled samples through evidence-label consistency and generates pseudo-labels from neighboring information. By assigning clean samples to optimize evidential networks and noisy samples to guide noise correlation matrices, respectively, TMNR$^{\mathbf{2}}$2 reduces mapping interference and achieves stabilized training. We empirically evaluate our methods against state-of-the-art baselines on 7 multi-view datasets. Experimental results demonstrate that TMNR$^{\mathbf{2}}$2 significantly outperforms baseline methods, with average accuracy improvements of 7% on datasets with 50% label noise.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Projects of Shaanxi Province
  • Xidian University Specially Funded Project for Interdisciplinary Exploration
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Zhang, Y., Xu, C., Jiang, H., Guan, Z., Zhao, W., He, X., & Sensoy, M. (2026). Trusted Multi-View Learning Under Noisy Supervision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(9), 10827-10843. https://doi.org/10.1109/tpami.2026.3690466

Vancouver

Zhang Y, Xu C, Jiang H, Guan Z, Zhao W, He X, et al. Trusted Multi-View Learning Under Noisy Supervision. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(9):10827-10843. doi:10.1109/tpami.2026.3690466

BibTeX
@article{Zhang2026,
  author = {Zhang, Yilin and Xu, Cai and Jiang, Han and Guan, Ziyu and Zhao, Wei and He, Xiaofei and Sensoy, Murat},
  title = {Trusted Multi-View Learning Under Noisy Supervision},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {9},
  pages = {10827--10843},
  doi = {10.1109/tpami.2026.3690466}
}
Kostenlos starten →