EUVIMEDEUVIMED entdecken
Crossref

Generalized Subspace Coupling Approach for Robust Low-Tubal-Rank Tensor Completion

Weichao Kong, Qingrong Feng, Qianyu Shu, Jianjun Wang, Tingwen Huang, Bin Zhang

IEEE Transactions on Neural Networks and Learning Systems · 2026-04 · 37 (4) · 1560-1574

DOI: 10.1109/tnnls.2025.3622331 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Neural Networks and Learning Systems, 2026-04. Verfasst von Weichao Kong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China’s Regional Innovation Development Joint Fund, Natural Science Foundation of Chongqing, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The field of low-tubal-rank tensor recovery, especially with subspace prior information, has recently garnered significant attention. However, existing methods encounter limitations when dealing with tensor data affected by simultaneous damage and loss. Moreover, they frequently necessitate clean (with no outliers) data to generate subspace prior information, which presents practical challenges. Addressing these issues, this article proposes a generalized subspace coupling (GSC) scheme, equipped with a novel tool to quantify the accuracy of the prior subspace. Building upon this foundation, we delve into the robust low-tubal-rank tensor completion problem, aiming to recover a low-tubal-rank tensor from partially observed data corrupted by sparse noise. Importantly, we theoretically demonstrate that the proposed method achieves exact tensor recovery under significantly weaker incoherence conditions compared to those previously suggested. Additionally, to optimize the proposed model, we design a symmetric Gauss-Seidel-based alternating direction method of multipliers (sGS-ADMM) with guaranteed convergence. Experiments conducted on various datasets, including facial images, medical scans, and video sequences, validate the superiority of our model over existing competitors in both qualitative and quantitative assessments.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China’s Regional Innovation Development Joint Fund
  • Natural Science Foundation of Chongqing, China
  • Key Research and Development Ecological Conservation and High-Quality Development of the Yellow River Basin Science and Technology of Ningxia
  • Construction Project of First-Class Subjects in Ningxia Higher Education

Zitieren

APA

Kong, W., Feng, Q., Shu, Q., Wang, J., Huang, T., & Zhang, B. (2026). Generalized Subspace Coupling Approach for Robust Low-Tubal-Rank Tensor Completion. IEEE Transactions on Neural Networks and Learning Systems, 37(4), 1560-1574. https://doi.org/10.1109/tnnls.2025.3622331

Vancouver

Kong W, Feng Q, Shu Q, Wang J, Huang T, Zhang B. Generalized Subspace Coupling Approach for Robust Low-Tubal-Rank Tensor Completion. IEEE Transactions on Neural Networks and Learning Systems. 2026;37(4):1560-1574. doi:10.1109/tnnls.2025.3622331

BibTeX
@article{Kong2026,
  author = {Kong, Weichao and Feng, Qingrong and Shu, Qianyu and Wang, Jianjun and Huang, Tingwen and Zhang, Bin},
  title = {Generalized Subspace Coupling Approach for Robust Low-Tubal-Rank Tensor Completion},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  year = {2026},
  volume = {37},
  number = {4},
  pages = {1560--1574},
  doi = {10.1109/tnnls.2025.3622331}
}
Kostenlos starten →