Cross-Domain Hyperspectral Image Classification Combined Sharpness-Aware Minimization with Local-to-Global Feature Enhancement
Remote Sensing · 28.02.2026 · 18 (5) · 740
DOI: 10.3390/rs18050740 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.02.2026. Verfasst von Chengyang Liu und 5 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key Research and Development Plan Project of Heilongjiang, the National Key Support Project for Foreign Experts of Northeast Special Project, the Program for Young Talents of Basic Research in Universities of Heilongjiang Province.
Abstract (Originalsprache)
With the increasing availability of satellite imagery and the shortening revisit intervals, efficiently processing satellite hyperspectral images has become a critical task. However, in practice, a large portion of satellite hyperspectral data remains unlabeled, making it difficult to achieve satisfactory classification performance using satellite data alone. Meanwhile, UAV-based platforms offer acquisition flexibility, which facilitates the collection of rich and detailed information. To address these challenges, this paper proposes a method called Sharpness-Aware Minimization with Local-to-Global Feature Enhancement (SAMLFE), which uses UAV hyperspectral images for training to enhance the fine-grained classification performance of satellite hyperspectral images in large scenes. Specifically, a spectral dimension mapping model is first employed to unify UAV and satellite images into a common spectral dimension, thereby mitigating the impact of inconsistent feature representations. Next, a local-to-global feature extraction network is constructed to capture both local details and global semantics. Few-shot learning is applied to extract discriminative features from both the source and target domains within the shared feature space, thereby enhancing the model’s ability to utilize limited labeled data efficiently. Furthermore, a conditional adversarial domain adaptation strategy is adopted to align the feature distributions of the source and target domains, thereby alleviating spectral shift. Meanwhile, the integration of an improved Sharpness-Aware Minimization (ISAM) enhances the model’s robustness across domains. Finally, the K-Nearest Neighbor algorithm is employed to perform accurate classification. Experimental results on multiple datasets demonstrate that the proposed method achieves superior generalization and classification performance in cross-domain hyperspectral image classification. It also outperforms existing methods in terms of feature distribution alignment, robustness of feature extraction, and adaptability to small-sample scenarios.
Förderung
- the Key Research and Development Plan Project of Heilongjiang
- the National Key Support Project for Foreign Experts of Northeast Special Project
- the Program for Young Talents of Basic Research in Universities of Heilongjiang Province
- the Postdoctoral Fellowship Program of China Postdoctoral Science Foundation
Zitieren
APA
Liu, C., Wang, A., Wang, M., Wu, H., Yan, S., & Zhao, L. (2026). Cross-Domain Hyperspectral Image Classification Combined Sharpness-Aware Minimization with Local-to-Global Feature Enhancement. Remote Sensing, 18(5), 740. https://doi.org/10.3390/rs18050740
Vancouver
Liu C, Wang A, Wang M, Wu H, Yan S, Zhao L. Cross-Domain Hyperspectral Image Classification Combined Sharpness-Aware Minimization with Local-to-Global Feature Enhancement. Remote Sensing. 2026;18(5):740. doi:10.3390/rs18050740
BibTeX
@article{Liu2026,
author = {Liu, Chengyang and Wang, Aili and Wang, Minhui and Wu, Haibin and Yan, Siqi and Zhao, Lin},
title = {Cross-Domain Hyperspectral Image Classification Combined Sharpness-Aware Minimization with Local-to-Global Feature Enhancement},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {5},
pages = {740},
doi = {10.3390/rs18050740}
}
EUVIMED