arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2603.03418cs.CV

mHC-HSI: 基于聚类的超连接Mamba用于超光谱图像分类

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

Department of Geomatics Engineering, University of Calgary（测绘工程系，卡尔加里大学）

Yimin Zhu, Zack Dewis, Quinn Ledingham, Saeid Taleghanidoozdoozan, Mabel Heffring, Zhengsen Xu, Motasem Alkayid, Megan Greenwood, Lincoln Linlin Xu

备注：
arXiv admin note: text overlap with arXiv:2601.15757
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出mHC-HSI模型，通过聚类引导的Mamba模块提升超光谱图像分类的准确性和可解释性。

摘要：

最近，DeepSeek提出了约束流形的超连接（mHC）方法，该方法在深度学习模型中相比传统残差连接表现出显著改进[1]。然而，这种方法尚未针对改进超光谱图像（HSI）分类进行专门设计。本文提出了一种基于聚类的mHC Mamba模型（mHC-HSI），以提升HSI分类性能，主要贡献包括：首先，为提高空间-光谱特征学习，我们设计了一个基于mHC框架的新型聚类引导Mamba模块，该模块明确学习HSI中的空间和光谱信息。其次，为将复杂的异质HSI分解为更小的聚类，我们设计了mHC中新的残差矩阵实现，该实现可视为软聚类成员图，从而提升mHC方法的可解释性。第三，为利用物理光谱知识，我们将光谱波段划分为具有物理意义的组，并将其作为mHC中的

英文摘要：

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

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑