arXiv 2407.082552024-07-11cs.CVcs.LG

GraphMamba：一种用于高光谱图像分类的高效图结构学习视觉Mamba

GraphMamba: An Efficient Graph Structure Learning Vision Mamba for Hyperspectral Image Classification

College of Electrical and Information Engineering, Hunan University（湖南大学电气与信息工程学院）；Peng Cheng Laboratory（鹏城实验室）；School of Information Engineering, Zhongnan University of Economics and Law（中南财经政法大学信息工程学院）；Emergency Management Research Center, Zhongnan University of Economics and Law（中南财经政法大学应急管理研究中心）

Aitao Yang, Min Li, Yao Ding, Leyuan Fang, Yaoming Cai, Yujie He

备注：: 13 pages, 10 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对高光谱图像分类中光谱特征捕获效率低、CNN空间上下文感知不灵活的问题，提出融合HyperMamba与SpectralGCN的GraphMamba框架，在三个真实数据集上取得了最优分类性能。

摘要：

高光谱图像分类中，光谱序列与地理空间信息的高效提取一直是研究热点。在光谱序列特征捕获方面，RNN和Transformer凭借其长距离特征捕获能力成为主流分类框架；在空间信息聚合方面，CNN通过扩大感受野尽可能保留完整的空间信息。然而，现有光谱特征捕获架构计算效率较低，且CNN缺乏感知空间上下文信息的灵活性。为解决这些问题，本文提出GraphMamba——一种高效的图结构学习视觉Mamba分类框架，该框架充分考虑高光谱图像（HSI）的特性，以实现深度空谱信息挖掘。具体而言，我们提出了一种新颖的高光谱视觉GraphMamba处理范式（HVGM），该范式通过构建空谱立方体保留空谱特征，并利用线性光谱编码提升后续任务的可操作性。GraphMamba的核心组件包括用于提升计算效率的HyperMamba模块和用于自适应空间上下文感知的SpectralGCN模块。HyperMamba采用全局掩码（GM）减轻杂波干扰，并引入并行训练推理架构缓解计算瓶颈；SpatialGCN融入加权多跳聚合（WMA）空间编码，聚焦高相关性的空间结构特征，从而在减轻空间噪声干扰的同时灵活聚合上下文信息。本文在三个不同规模的真实HSI数据集上开展了大量实验，与现有最优分类框架相比，GraphMamba取得了最优性能。

英文摘要：

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.

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。

AI总结：

摘要：

英文摘要：

相关论文