A multi-scale CNN–SENet front-end plus stacked Mamba blocks and center/global aggregation reaches top reported OA on Indian Pines, HongHu, and Salinas with ~0.2M parameters.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
MSCM-net: A hyperspectral image classiffcation method based on multi-scale convolution and Mamba
A multi-scale CNN–SENet front-end plus stacked Mamba blocks and center/global aggregation reaches top reported OA on Indian Pines, HongHu, and Salinas with ~0.2M parameters.