HyperSMamba: A Lightweight Mamba for Efficient Hyperspectral Image Classification
Remote Sensing · 11.06.2025 · 17 (12) · 2008
DOI: 10.3390/rs17122008 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 11.06.2025. Verfasst von Mengyuan Sun und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Deep learning has recently achieved remarkable progress in hyperspectral image (HSI) classification. Among these advancements, the Transformer-based models have gained considerable attention due to their ability to establish long-range dependencies. However, the quadratic computational complexity of the self-attention mechanism limits its application in hyperspectral image classification (HSIC). Recently, the Mamba architecture has shown outstanding performance in 1D sequence modeling tasks owing to its lightweight linear sequence operations and efficient parallel scanning capabilities. Nevertheless, its application in HSI classification still faces challenges. Most existing Mamba-based approaches adopt various selective scanning strategies for HSI serialization, ensuring the adjacency of scanning sequences to enhance spatial continuity. However, these methods lead to substantially increased computational overhead. To overcome these challenges, this study proposes the Hyperspectral Spatial Mamba (HyperSMamba) model for HSIC, aiming to reduce computational complexity while improving classification performance. The suggested framework consists of the following key components: (1) a Multi-Scale Spatial Mamba (MS-Mamba) encoder, which refines the state-space model (SSM) computation by incorporating a Multi-Scale State Fusion Module (MSFM) after the state transition equations of original SSMs. This module aggregates adjacent state representations to reinforce spatial dependencies among local features; (2) our proposed Adaptive Fusion Attention Module (AFAttention) to dynamically fuse bidirectional Mamba outputs for optimizing feature representation. Experiments were performed on three HSI datasets, and the findings demonstrate that HyperSMamba attains overall accuracy of 94.86%, 97.72%, and 97.38% on the Indian Pines, Pavia University, and Salinas datasets, while maintaining low computational complexity. These results confirm the model’s effectiveness and potential for practical application in HSIC tasks.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Sun, M., Wang, L., Jiang, S., Cheng, S., & Tang, L. (2025). HyperSMamba: A Lightweight Mamba for Efficient Hyperspectral Image Classification. Remote Sensing, 17(12), 2008. https://doi.org/10.3390/rs17122008
Vancouver
Sun M, Wang L, Jiang S, Cheng S, Tang L. HyperSMamba: A Lightweight Mamba for Efficient Hyperspectral Image Classification. Remote Sensing. 2025;17(12):2008. doi:10.3390/rs17122008
BibTeX
@article{Sun2025,
author = {Sun, Mengyuan and Wang, Liejun and Jiang, Shaochen and Cheng, Shuli and Tang, Lihan},
title = {HyperSMamba: A Lightweight Mamba for Efficient Hyperspectral Image Classification},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {12},
pages = {2008},
doi = {10.3390/rs17122008}
}
EUVIMED