EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HyperspectralMamba: A Novel State Space Model Architecture for Hyperspectral Image Classification

Jianshang Liao, Liguo Wang

Remote Sensing · 24.07.2025 · 17 (15) · 2577

DOI: 10.3390/rs17152577 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.07.2025. Verfasst von Jianshang Liao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Guangdong, Special Projects in Key Areas of Guangdong Province, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hyperspectral image classification faces challenges with high-dimensional spectral data and complex dependencies between bands. This paper proposes HyperspectralMamba, a novel architecture for hyperspectral image classification that integrates state space modeling with adaptive recalibration mechanisms. The method addresses limitations in existing techniques through three key innovations: (1) a novel dual-stream architecture that combines SSM global modeling with parallel convolutional local feature extraction, distinguishing our approach from existing single-stream SSM methods; (2) a band-adaptive feature recalibration mechanism specifically designed for hyperspectral data that adaptively adjusts the importance of different spectral band features; and (3) an effective feature fusion strategy that integrates global and local features through residual connections. Experimental results on three benchmark datasets—Indian Pines, Pavia University, and Salinas Valley—demonstrate that the proposed method achieves overall accuracies of 95.31%, 98.60%, and 96.40%, respectively, significantly outperforming existing convolutional neural networks, attention-enhanced networks, and Transformer methods. HyperspectralMamba demonstrates an exceptional performance in small-sample class recognition and distinguishing spectrally similar terrain, while maintaining lower computational complexity, providing a new technical approach for high-precision hyperspectral image classification.

Förderung

  • Natural Science Foundation of Guangdong
  • Special Projects in Key Areas of Guangdong Province
  • National Natural Science Foundation of China

Zitieren

APA

Liao, J., & Wang, L. (2025). HyperspectralMamba: A Novel State Space Model Architecture for Hyperspectral Image Classification. Remote Sensing, 17(15), 2577. https://doi.org/10.3390/rs17152577

Vancouver

Liao J, Wang L. HyperspectralMamba: A Novel State Space Model Architecture for Hyperspectral Image Classification. Remote Sensing. 2025;17(15):2577. doi:10.3390/rs17152577

BibTeX
@article{Liao2025,
  author = {Liao, Jianshang and Wang, Liguo},
  title = {HyperspectralMamba: A Novel State Space Model Architecture for Hyperspectral Image Classification},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {15},
  pages = {2577},
  doi = {10.3390/rs17152577}
}
Kostenlos starten →