A new unmixing-guided spatial-spectral Mamba model with Top-K clustering tokens jointly learns endmembers, abundances, and class labels to outperform prior methods on hyperspectral image classification.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unmixing-Guided Spatial-Spectral Mamba with Clustering Tokens for Hyperspectral Image Classification
A new unmixing-guided spatial-spectral Mamba model with Top-K clustering tokens jointly learns endmembers, abundances, and class labels to outperform prior methods on hyperspectral image classification.