3DSS-Mamba：用于高光谱图像分类的3D光谱-空间Mamba
3DSS-Mamba: 3D-Spectral-Spatial Mamba for Hyperspectral Image Classification
AI总结：
本文提出3DSS-Mamba框架，通过3D光谱-空间令牌生成与选择性扫描机制，高效建模高光谱图像的全局光谱-空间关系，在HSI分类基准上超越现有最先进方法。
摘要：
高光谱图像（HSI）分类是遥感领域的基础研究。卷积神经网络（CNN）和Transformer在捕获光谱-空间上下文依赖关系方面已展现出卓越的能力。然而，这些架构分别受限于有限的感受野和二次方的计算复杂度。幸运的是，最近构建于状态空间模型之上的Mamba架构融合了长程序列建模和线性计算效率的优势，在低维场景中展现出巨大潜力。受此启发，我们提出了一种新颖的3D-光谱-空间Mamba（3DSS-Mamba）框架用于HSI分类，能够以更高的计算效率实现全局光谱-空间关系建模。在技术层面，设计了一个光谱-空间令牌生成（SSTG）模块，将HSI立方体转换为一组3D光谱-空间令牌。为了克服传统Mamba仅限于建模因果序列且难以适应高维场景的局限性，引入了一种3D-光谱-空间选择性扫描（3DSS）机制，该机制沿光谱维度和空间维度对3D高光谱令牌执行逐像素选择性扫描。构建了五条扫描路径以研究维度优先级的影响。3DSS扫描机制与常规映射操作相结合，形成3D-光谱-空间mamba块（3DMB），从而能够提取全局光谱-空间语义表示。实验结果与分析表明，所提出的方法在HSI分类基准上优于当前最先进的方法。
英文摘要：
Hyperspectral image (HSI) classification constitutes the fundamental research in remote sensing fields. Convolutional Neural Networks (CNNs) and Transformers have demonstrated impressive capability in capturing spectral-spatial contextual dependencies. However, these architectures suffer from limited receptive fields and quadratic computational complexity, respectively. Fortunately, recent Mamba architectures built upon the State Space Model integrate the advantages of long-range sequence modeling and linear computational efficiency, exhibiting substantial potential in low-dimensional scenarios. Motivated by this, we propose a novel 3D-Spectral-Spatial Mamba (3DSS-Mamba) framework for HSI classification, allowing for global spectral-spatial relationship modeling with greater computational efficiency. Technically, a spectral-spatial token generation (SSTG) module is designed to convert the HSI cube into a set of 3D spectral-spatial tokens. To overcome the limitations of traditional Mamba, which is confined to modeling causal sequences and inadaptable to high-dimensional scenarios, a 3D-Spectral-Spatial Selective Scanning (3DSS) mechanism is introduced, which performs pixel-wise selective scanning on 3D hyperspectral tokens along the spectral and spatial dimensions. Five scanning routes are constructed to investigate the impact of dimension prioritization. The 3DSS scanning mechanism combined with conventional mapping operations forms the 3D-spectral-spatial mamba block (3DMB), enabling the extraction of global spectral-spatial semantic representations. Experimental results and analysis demonstrate that the proposed method outperforms the state-of-the-art methods on HSI classification benchmarks.
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。
