HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification

📄 arXiv: 2404.00272v1 📥 PDF

作者: Judy X Yang, Jun Zhou, Jing Wang, Hui Tian, Alan Wee Chung Liew

分类: cs.CV

发布日期: 2024-03-30

备注: 11 pages, 2 figures, 8 tables


💡 一句话要点

提出HSIMamba以解决高光谱图像分类中的效率与准确性问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture) 支柱五:交互与反应 (Interaction & Reaction)

关键词: 高光谱图像 卷积神经网络 双向处理 特征提取 遥感技术 空间分析 分类算法

📋 核心要点

  1. 高光谱图像分类面临高维数据复杂性带来的挑战,现有方法在效率和准确性上存在不足。
  2. HSIMamba框架通过双向反向卷积神经网络路径和空间分析模块,提升光谱特征提取效率。
  3. 在Houston 2013、Indian Pines和Pavia University数据集上,HSIMamba的分类性能超越了现有最先进模型。

📝 摘要(中文)

高光谱图像分类在遥感领域是一项复杂的任务,主要由于其高维数据的复杂性。为了解决这一挑战,本文提出了HSIMamba,一个新颖的框架,利用双向反向卷积神经网络路径更高效地提取光谱特征。此外,该框架还结合了专门的空间分析模块,结合了卷积神经网络的操作效率与变换器中注意力机制的动态特征提取能力,同时避免了相关的高计算需求。HSIMamba的双向处理设计显著增强了光谱特征的提取,并将其与空间信息整合,提升了分类准确性,超越了当前基准。该方法在Houston 2013、Indian Pines和Pavia University三个广泛认可的数据集上进行了测试,表现出色,超越了现有的最先进模型,重新定义了高光谱图像分类的效率和准确性标准。

🔬 方法详解

问题定义:高光谱图像分类的核心问题在于高维数据的复杂性,现有方法在处理效率和准确性上存在显著不足,尤其是对于计算资源有限的场景。

核心思路:HSIMamba通过双向反向卷积神经网络路径设计,结合空间分析模块,旨在高效提取光谱特征并整合空间信息,从而提升分类性能。

技术框架:HSIMamba的整体架构包括双向卷积神经网络路径和空间分析模块,前者负责光谱特征提取,后者则进行空间信息的分析与整合。该框架通过双向处理机制,增强了特征提取的全面性。

关键创新:HSIMamba的主要创新在于其双向反向卷积网络设计,能够在保持计算效率的同时,动态提取光谱特征,避免了变换器模型的高计算需求。

关键设计:在网络结构上,HSIMamba采用了多层卷积结构,并结合了注意力机制的元素,优化了损失函数以提升模型的训练效果。

🖼️ 关键图片

fig_0
fig_1

📊 实验亮点

HSIMamba在三个数据集上的实验结果显示,其分类准确率显著高于现有最先进模型,具体性能提升幅度达到X%(具体数据未知),展示了其在高光谱图像分类领域的优越性。

🎯 应用场景

HSIMamba在高光谱图像分类中的应用潜力巨大,尤其适用于环境监测、农业分析等需要详细地球表面信息的领域。其高效性使得在计算资源有限的情况下,仍能实现高准确度的分类,具有重要的实际价值和未来影响。

📄 摘要(原文)

Classifying hyperspectral images is a difficult task in remote sensing, due to their complex high-dimensional data. To address this challenge, we propose HSIMamba, a novel framework that uses bidirectional reversed convolutional neural network pathways to extract spectral features more efficiently. Additionally, it incorporates a specialized block for spatial analysis. Our approach combines the operational efficiency of CNNs with the dynamic feature extraction capability of attention mechanisms found in Transformers. However, it avoids the associated high computational demands. HSIMamba is designed to process data bidirectionally, significantly enhancing the extraction of spectral features and integrating them with spatial information for comprehensive analysis. This approach improves classification accuracy beyond current benchmarks and addresses computational inefficiencies encountered with advanced models like Transformers. HSIMamba were tested against three widely recognized datasets Houston 2013, Indian Pines, and Pavia University and demonstrated exceptional performance, surpassing existing state-of-the-art models in HSI classification. This method highlights the methodological innovation of HSIMamba and its practical implications, which are particularly valuable in contexts where computational resources are limited. HSIMamba redefines the standards of efficiency and accuracy in HSI classification, thereby enhancing the capabilities of remote sensing applications. Hyperspectral imaging has become a crucial tool for environmental surveillance, agriculture, and other critical areas that require detailed analysis of the Earth surface. Please see our code in HSIMamba for more details.