GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image Classification
Aitao Yang, Min Li, Yao Ding, Leyuan Fang, Yaoming Cai, Yujie He
TL;DR
This work tackles hyperspectral image classification under spectral redundancy and limited spatial resolution. It proposes GraphMamba, a Graph-structure learning vision Mamba framework, including HVGM for spatial-spectral cubes, HyperMamba for spectral efficiency, and SpatialGCN for adaptive spatial context. The approach yields state-of-the-art accuracy on IP, SA, and UH2013 with reduced computational cost, thanks to parallel processing and multi-hop adaptive neighborhood encoding. The results demonstrate a scalable, information-rich method for joint spatial-spectral feature extraction with strong edge preservation and robustness to training data size.
Abstract
Efficient extraction of spectral sequences and geospatial information has always been a hot topic in hyperspectral image classification. In terms of spectral sequence feature capture, RNN and Transformer have become mainstream classification frameworks due to their long-range feature capture capabilities. In terms of spatial information aggregation, CNN enhances the receptive field to retain integrated spatial information as much as possible. However, the spectral feature-capturing architectures exhibit low computational efficiency, and CNNs lack the flexibility to perceive spatial contextual information. To address these issues, this paper proposes GraphMamba--an efficient graph structure learning vision Mamba classification framework that fully considers HSI characteristics to achieve deep spatial-spectral information mining. Specifically, we propose a novel hyperspectral visual GraphMamba processing paradigm (HVGM) that preserves spatial-spectral features by constructing spatial-spectral cubes and utilizes linear spectral encoding to enhance the operability of subsequent tasks. The core components of GraphMamba include the HyperMamba module for improving computational efficiency and the SpectralGCN module for adaptive spatial context awareness. The HyperMamba mitigates clutter interference by employing the global mask (GM) and introduces a parallel training inference architecture to alleviate computational bottlenecks. The SpatialGCN incorporates weighted multi-hop aggregation (WMA) spatial encoding to focus on highly correlated spatial structural features, thus flexibly aggregating contextual information while mitigating spatial noise interference. Extensive experiments were conducted on three different scales of real HSI datasets, and compared with the state-of-the-art classification frameworks, GraphMamba achieved optimal performance.