Efficient One-Step Orthogonal Consensus Framework for Multiview Remote Sensing Clustering
IEEE Transactions on Geoscience and Remote Sensing · 2026 · 64 · 1-15
DOI: 10.1109/tgrs.2026.3666477 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2026. Verfasst von Haoyan Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangxi Science and Technology Major Program, Innovation Project of Guangxi Graduate Education.
Abstract (Originalsprache)
Jointly clustering multisource remote sensing (RS) data remains challenging despite the promising progress of multiview clustering (MVC). Many existing methods have several limitations: 1) two-stage pipelines that separate feature learning from clustering often incur error accumulation and lead to blurred land-cover boundaries; 2) fixed or equal-view fusion cannot adapt to heterogeneous view quality, allowing noisy or redundant views to dominate the consensus representation; and 3) the construction of full affinity matrices results in high computational cost, restricting scalability for large RS data. To address these issues, we propose an efficient one-step orthogonal consensus (EO2C) framework for multiview RS clustering. EO2C first performs superpixel-guided spatial denoising to obtain reliable and spatially coherent features. It then learns structure-consistent embeddings by jointly optimizing the embedding, mapping matrix, and cluster indicator matrix, thereby preserving view-specific local structures. More importantly, an adaptive consensus fusion strategy based on a collective orthogonality constraint projects reconstructed view-specific representations into a shared consensus space while automatically regulating view contributions to suppress unreliable views. These components collectively enable EO2C to achieve robust, discriminative, and one-step clustering. An efficient alternating optimization algorithm further attains near-linear computational complexity via closed-form or orthogonal updates. Extensive experiments on four real-world multisource RS datasets demonstrate that EO2C outperforms state-of-the-art methods in clustering performance. The code is available at https://github.com/ytccyw/EO2C
Förderung
- National Natural Science Foundation of China
- Guangxi Science and Technology Major Program
- Innovation Project of Guangxi Graduate Education
Zitieren
APA
Yang, H., Yang, L., Wu, T. X., Yang, T., Liang, L., & Tang, Y. Y. (2026). Efficient One-Step Orthogonal Consensus Framework for Multiview Remote Sensing Clustering. IEEE Transactions on Geoscience and Remote Sensing, 64, 1-15. https://doi.org/10.1109/tgrs.2026.3666477
Vancouver
Yang H, Yang L, Wu TX, Yang T, Liang L, Tang YY. Efficient One-Step Orthogonal Consensus Framework for Multiview Remote Sensing Clustering. IEEE Transactions on Geoscience and Remote Sensing. 2026;64:1-15. doi:10.1109/tgrs.2026.3666477
BibTeX
@article{Yang2026,
author = {Yang, Haoyan and Yang, Lina and Wu, Thomas Xinzhang and Yang, Tianchuan and Liang, Lianhui and Tang, Yuan Yan},
title = {Efficient One-Step Orthogonal Consensus Framework for Multiview Remote Sensing Clustering},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2026},
volume = {64},
pages = {1--15},
doi = {10.1109/tgrs.2026.3666477}
}
EUVIMED