Clustering-Guided Spatial-Spectral Mamba for Hyperspectral Image Classification

TL;DR

This paper introduces CSSMamba, a novel hyperspectral image classification framework that combines clustering, spatial-spectral Mamba models, and attention mechanisms to enhance accuracy and boundary preservation.

Contribution

The paper proposes a clustering-guided spatial-spectral Mamba framework with adaptive token sequencing and learnable clustering for improved hyperspectral image classification.

Findings

CSSMamba outperforms state-of-the-art methods on multiple datasets.

It achieves higher classification accuracy and better boundary preservation.

The framework effectively integrates clustering with Mamba models.

Abstract

Although Mamba models greatly improve Hyperspectral Image (HSI) classification, they have critical challenges in terms defining efficient and adaptive token sequences for improve performance. This paper therefore presents CSSMamba (Clustering-guided Spatial-Spectral Mamba) framework to better address the challenges, with the following contributions. First, to achieve efficient and adaptive token sequences for improved Mamba performance, we integrate the clustering mechanism into a spatial Mamba architecture, leading to a cluster-guided spatial Mamba module (CSpaMamba) that reduces the Mamba sequence length and improves Mamba feature learning capability. Second, to improve the learning of both spatial and spectral information, we integrate the CSpaMamba module with a spectral mamba module (SpeMamba), leading to a complete clustering-guided spatial-spectral Mamba framework. Third, to further improve feature learning capability, we introduce an Attention-Driven Token Selection mechanism to optimize Mamba token sequencing. Last, to seamlessly integrate clustering into the Mamba model in a coherent manner, we design a Learnable Clustering Module that learns the cluster memberships in an adaptive manner. Experiments on the Pavia University, Indian Pines, and Liao-Ning 01 datasets demonstrate that CSSMamba achieves higher accuracy and better boundary preservation compared to state-of-the-art CNN, Transformer, and Mamba-based methods.