AI RESEARCH
Unmixing-Guided Spatial-Spectral Mamba with Clustering Tokens for Hyperspectral Image Classification
arXiv CS.CV
•
ArXi:2604.09948v1 Announce Type: new Although hyperspectral image (HSI) classification is critical for ing various environmental applications, it is a challenging task due to the spectral-mixture effect, the spatial-spectral heterogeneity and the difficulty to preserve class boundaries and details. This letter presents a novel unmixing-guided spatial-spectral Mamba with clustering tokens for improved HSI classification, with the following contributions.