EUVIMEDEUVIMED entdecken
Crossref

Learning Compact Semantic Information and Reliable Pseudo-Labels for Incomplete Multi-View Multi-Label Classification

Yadong Liu, Chengliang Liu, Jie Wen, Li Shen, Bob Zhang, Yong Xu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-07 · 48 (7) · 7575-7589

DOI: 10.1109/tpami.2026.3665813 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-07. Verfasst von Yadong Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 74 Literaturangaben. Gefördert von: Shenzhen Science and Technology Program, Project of Xiangjiang Laboratory, Basic and Applied Basic Research Foundation of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-view data encompasses various data types, including multi-feature, multi-sequence, and multi-modal data. Multi-view multi-label classification aims to leverage the rich semantic information contained in multiple views to achieve enhanced multi-label classification performance. In practical applications, the absence of views and labels poses a significant challenge to multi-view multi-label classification tasks. Premised on the assumption that shared semantic information across multiple views is sufficient to support the downstream task, we propose CTRL, a novel incomplete multi-view multi-label classification framework to address the multi-view learning challenge on the data with partially missing views and missing labels in this paper. The core mechanism of CTRL lies in learning a high-purity, low-redundancy condensed representation that adequately captures the essential information of the original data. Specifically, we design a new objective loss to enhance the semantic information of shared cross-view within the joint representation learning process while simultaneously suppressing intra-view redundant information that is irrelevant to the downstream task. This enables CTRL to extract task-relevant representations even when views are incomplete. Furthermore, we employ the Beta Evidential Neural Network to model the label distribution. This network is then integrated with Dempster-Shafer theory, enabling our model to perform label-level classification uncertainty estimation. This also allows us to use the estimated uncertainty and belief mass to create high-reliability pseudo-labels, resulting in further gains in model performance. Experimental results on multiple benchmark datasets demonstrate the superior performance of our proposed model in terms of accuracy, robustness, and reliability.

Förderung

  • Shenzhen Science and Technology Program
  • Project of Xiangjiang Laboratory
  • Basic and Applied Basic Research Foundation of Guangdong Province
  • National Natural Science Foundation of China

Zitieren

APA

Liu, Y., Liu, C., Wen, J., Shen, L., Zhang, B., & Xu, Y. (2026). Learning Compact Semantic Information and Reliable Pseudo-Labels for Incomplete Multi-View Multi-Label Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(7), 7575-7589. https://doi.org/10.1109/tpami.2026.3665813

Vancouver

Liu Y, Liu C, Wen J, Shen L, Zhang B, Xu Y. Learning Compact Semantic Information and Reliable Pseudo-Labels for Incomplete Multi-View Multi-Label Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(7):7575-7589. doi:10.1109/tpami.2026.3665813

BibTeX
@article{Liu2026,
  author = {Liu, Yadong and Liu, Chengliang and Wen, Jie and Shen, Li and Zhang, Bob and Xu, Yong},
  title = {Learning Compact Semantic Information and Reliable Pseudo-Labels for Incomplete Multi-View Multi-Label Classification},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {7},
  pages = {7575--7589},
  doi = {10.1109/tpami.2026.3665813}
}
Kostenlos starten →