EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Scale Semantic Selection and Spatial Constraint-Guided Network for Cross-Scene Hyperspectral Image Classification

Yuntao Tang, Yu Sun, Xuyang Teng iD, Cuiping Yang iD, Ruifeng Xie iD, Xiaojun Guan, Xiaodong Yu iD

Sensors · 21.07.2026 · 26 (14) · 4627

DOI: 10.3390/s26144627 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.07.2026. Verfasst von Yuntao Tang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Information Engineering, Harbin Normal University, Harbin 150025, China. Die Arbeit nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Heilongjiang Provincial Natural Science Foundation of China, Basic Research Projects of Universities in Heilongjiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-scene classification of hyperspectral images attracts extensive research attention due to the prominent distribution discrepancies existing in hyperspectral images across different scenes. Most existing methods mitigate domain shift by expanding source domain samples and aligning feature distributions. However, these approaches fail to fully explore the spatial semantics of samples during the expansion process. Moreover, features are compressed into one-dimensional vectors in the alignment stage, resulting in the loss of critical spatial location information. To address the above issues, this paper proposes a multi-scale semantic selection and spatial constraint-guided network (MSCGnet). Specifically, the multi-scale semantic selection generator adopts a spatial diffusion scanning strategy to optimize the token serialization rule of Mamba. Pixels are arranged from the center to the periphery to maintain spatial continuity. Combined with the multi-scale semantic selection routing, multi-scale spectral–spatial features are extracted and a semantic selection matrix is constructed to guide Mamba to generate diverse augmented samples. The spatial constraint-guided discriminator leverages class activation map projection to impose explicit spatial constraints on feature distributions, further improving the reliability of augmented samples. Comprehensive experiments on multiple cross-scene HSI datasets demonstrate that the proposed method achieves superior classification accuracy and generalization performance with low model complexity.

Schlagwörter

Stichwörter der Autor:innen

cross-scene classificationdomain generalizationhyperspectral imagemulti-scale semanticsspatial constraint

Autor:innen und Institutionen

  • College of Computer Science and Information Engineering, Harbin Normal University, Harbin 150025, China.
  • Department of Municipal and Environmental Engineering, Harbin Vocational University of Architectural Technology, Harbin 150025, China.
  • School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China.
  • College of Geography Science, Harbin Normal University, Harbin 150025, China.
  • Teaching Experiment Equipment Management Center, Harbin Normal University, Harbin 150025, China.

ORCID-Profile: Xuyang Teng, Cuiping Yang, Ruifeng Xie, Xiaodong Yu

Förderung

  • Heilongjiang Provincial Natural Science Foundation of China
  • Basic Research Projects of Universities in Heilongjiang Province

Zitieren

APA

Tang, Y., Sun, Y., Teng, X., Yang, C., Xie, R., Guan, X., & Yu, X. (2026). Multi-Scale Semantic Selection and Spatial Constraint-Guided Network for Cross-Scene Hyperspectral Image Classification. Sensors, 26(14), 4627. https://doi.org/10.3390/s26144627

Vancouver

Tang Y, Sun Y, Teng X, Yang C, Xie R, Guan X, et al. Multi-Scale Semantic Selection and Spatial Constraint-Guided Network for Cross-Scene Hyperspectral Image Classification. Sensors. 2026;26(14):4627. doi:10.3390/s26144627

BibTeX
@article{Tang2026,
  author = {Tang, Yuntao and Sun, Yu and Teng, Xuyang and Yang, Cuiping and Xie, Ruifeng and Guan, Xiaojun and Yu, Xiaodong},
  title = {Multi-Scale Semantic Selection and Spatial Constraint-Guided Network for Cross-Scene Hyperspectral Image Classification},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {14},
  pages = {4627},
  doi = {10.3390/s26144627}
}
Kostenlos starten →