Clustering-Guided Spatial-Spectral Mamba for Hyperspectral Image Classification

2026-01-22

AI Summary

This work proposes CSSMamba, a novel framework addressing the challenge of efficiently and adaptively constructing token sequences for hyperspectral image classification with Mamba-based models. CSSMamba integrates a clustering-guided spatial Mamba module (CSpaMamba) and a spectral Mamba module (SpeMamba), augmented by an attention-driven token selection mechanism and a learnable clustering module to enable joint spatial-spectral modeling and adaptive token sequence formation. Experimental results demonstrate that CSSMamba significantly outperforms state-of-the-art CNNs, Transformers, and existing Mamba-based approaches on the Pavia University, Indian Pines, and Liao-Ning 01 datasets, achieving leading performance in both classification accuracy and boundary preservation.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

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.

Problem

• Hyperspectral Image Classification
• Mamba Model
• Token Sequence
• Spatial-Spectral Feature Learning
• Efficient Representation

Innovation

• Mamba
• hyperspectral image classification
• clustering-guided tokenization
• spatial-spectral modeling
• attention-driven token selection