Multi-head Spatial-Spectral Mamba for Hyperspectral Image Classification
arXiv:2408.01224 · doi:10.1080/2150704X.2025.2461330
Abstract
Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high dimensionality and sequential data. To address these issues, we propose the SSM with multi-head self-attention and token enhancement (MHSSMamba). This model integrates spectral and spatial information by enhancing spectral tokens and using multi-head attention to capture complex relationships between spectral bands and spatial locations. It also manages long-range dependencies and the sequential nature of HSI data, preserving contextual information across spectral bands. MHSSMamba achieved remarkable classification accuracies of 97.62\% on Pavia University, 96.92\% on the University of Houston, 96.85\% on Salinas, and 99.49\% on Wuhan-longKou datasets. The source code is available at \href{https://github.com/MHassaanButt/MHA\_SS\_Mamba}{GitHub}.
References in corpus (9)
- MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification
- A Fast 3D CNN for Hyperspectral Image Classification
- Spectral-Spatial Mamba for Hyperspectral Image Classification
- WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image Classification
- SpectralMamba: Efficient Mamba for Hyperspectral Image Classification
- Pyramid Hierarchical Transformer for Hyperspectral Image Classification
- Transformers Fusion across Disjoint Samples for Hyperspectral Image Classification
- HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification
- Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral Image Classification
Cited by in corpus (5)
- A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models
- Spatial and Spatial-Spectral Morphological Mamba for Hyperspectral Image Classification
- DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification
- Transformer-Driven Active Transfer Learning for Cross-Hyperspectral Image Classification
- EnergyFormer: Energy Attention with Fourier Embedding for Hyperspectral Image Classification