Mamba-Driven Multi-Scale Spatial-Spectral Fusion Network for Few-Shot Hyperspectral Image Classification

The core of hyperspectral image (HSI) classification lies in the effective fusion of spatial-spectral features. However, traditional methods are limited by the capacity of handcrafted feature representation, while deep learning methods face challenges such as overfitting with small sample sizes and high computational complexity. This paper proposes a Mamba-driven multi-scale spatial-spectral fusion network (M 2 S 2 F-Net). This network extracts spatial-spectral features at different granularities through the Spatial-Spectral Multi-Granularity Feature Extraction Module (SSMG-FEM), adaptively enhances the spatial-spectral correlation through the Spatial-Spectral Fusion Attention Module (SSFAM), optimizes feature fusion by combining local and global streams with the Feature Fusion Enhanced Vision Transformer (FFEVT), and establishes long- sequence dependencies using the Dual-Path Feature Fusion Mamba (DPFFM). The M 2 S 2 F-Net employs a multi-stage feature fusion strategy of “ coarse fusion-fine optimization-strong screening ” to achieve efficient classification with few samples. The network was validated on three publicly available HSI datasets to demonstrate its superiority in few-shot scenarios, with significant improvements in classification accuracy. It also exhibited remarkable classification performance across different numbers of training samples.