mHC-HSI: Clustering-Guided Hyper-Connection Mamba for Hyperspectral Image Classification

TL;DR

This paper introduces mHC-HSI, a clustering-guided hyper-connection model that improves hyperspectral image classification by learning spatial-spectral features, decomposing HSI into meaningful clusters, and leveraging physical spectral knowledge for better accuracy and interpretability.

Contribution

The paper proposes a novel clustering-guided mHC Mamba model tailored for hyperspectral image classification, enhancing feature learning, explainability, and physical interpretability.

Findings

Improved classification accuracy on benchmark datasets.

Enhanced model explainability through soft cluster membership maps.

Leveraged physical spectral band grouping for interpretability.

Abstract

Recently, DeepSeek has invented the manifold-constrained hyper-connection (mHC) approach which has demonstrated significant improvements over the traditional residual connection in deep learning models \cite{xie2026mhc}. Nevertheless, this approach has not been tailor-designed for improving hyperspectral image (HSI) classification. This paper presents a clustering-guided mHC Mamba model (mHC-HSI) for enhanced HSI classification, with the following contributions. First, to improve spatial-spectral feature learning, we design a novel clustering-guided Mamba module, based on the mHC framework, that explicitly learns both spatial and spectral information in HSI. Second, to decompose the complex and heterogeneous HSI into smaller clusters, we design a new implementation of the residual matrix in mHC, which can be treated as soft cluster membership maps, leading to improved explainability of the mHC approach. Third, to leverage the physical spectral knowledge, we divide the spectral bands into physically-meaningful groups and use them as the "parallel streams" in mHC, leading to a physically-meaningful approach with enhanced interpretability. The proposed approach is tested on benchmark datasets in comparison with the state-of-the-art methods, and the results suggest that the proposed model not only improves the accuracy but also enhances the model explainability. Code is available here: https://github.com/GSIL-UCalgary/mHC_HyperSpectral