用三维离散余弦变换和状态空间模型提升高光谱图像分类精度
DCT-Mamba3D: Spectral Decorrelation and Spatial-Spectral Feature Extraction for Hyperspectral Image Classification
- 通过三维离散余弦变换消除光谱与空间冗余，提升特征清晰度
- 采用双向状态空间模型捕捉复杂的空间-光谱依赖关系
- 适合处理光谱相似或空间重叠的高光谱图像分类难题
高光谱图像分类面临光谱冗余和复杂空间-光谱依赖的挑战。本文提出一种新框架 DCT-Mamba3D。该框架包含：(1) 3D 光谱-空间去相关模块，利用 3D 离散余弦变换基函数同时降低光谱与空间冗余，增强多维特征清晰度；(2) 3D-Mamba 模块，基于双向状态空间模型捕获精细的空间-光谱依赖关系；(3) 全局残差增强模块，稳定特征表示，提升鲁棒性与收敛性。在多个基准数据集上的大量实验表明，DCT-Mamba3D 在同类物体不同光谱、不同物体相同光谱等复杂场景下优于当前最优方法。
原文摘要 · Abstract (English)
Hyperspectral image classification presents challenges due to spectral redundancy and complex spatial-spectral dependencies. This paper proposes a novel framework, DCT-Mamba3D, for hyperspectral image classification. DCT-Mamba3D incorporates: (1) a 3D spectral-spatial decorrelation module that applies 3D discrete cosine transform basis functions to reduce both spectral and spatial redundancy, enhancing feature clarity across dimensions; (2) a 3D-Mamba module that leverages a bidirectional state-space model to capture intricate spatial-spectral dependencies; and (3) a global residual enhancement module that stabilizes feature representation, improving robustness and convergence. Extensive experiments on benchmark datasets show that our DCT-Mamba3D outperforms the state-of-the-art methods in challenging scenarios such as the same object in different spectra and different objects in the same spectra.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。