基于Token聚类与语义序列Mamba的高光谱图像分类
原标题：Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification
AI 摘要
该论文提出 STMamba，一种用于高光谱图像分类的新方法，通过 Token Clustering Module 将稀疏 token 组织成语义一致的序列，并利用并行的空间与光谱语义序列 Mamba 模块捕获长程依赖。方法在宏观层面采用层次化编码器-解码器与无参数跨尺度邻域注意力上采样器，微观层面通过密度感知聚类和四叉树动态选择保留代表性 token。在三个大规模基准数据集上，STMamba 在定量和定性结果上均优于现有最先进方法。
正文节选
Token Clustering and Semantic Sequence Mamba for Hyperspectral Image Classification Abstract Although hyperspectral images (HSIs) provide rich spectral-spatial information, accurate pixel-level classification remains challenging because of spectral-spatial heterogeneity and complex spatial structures. Existing vision state-space models (Mamba) typically construct sequences according to predefined spatial neighborhoods, without explicitly accounting for semantic similarity or spatial non-stationa