Abstract: As one of the fundamental research topics in remote sensing image analysis ... named compact and discriminative stacked autoencoder (CDSAE), for HSI classification. The proposed CDSAE ...

Abstract: Due to the excellent feature extraction capabilities, deep learning has become the mainstream method for hyperspectral image (HSI ... hierarchical multiscale transformer-based masked ...

Deep learning has been widely applied to high-dimensional hyperspectral image classification and has achieved ... we propose a multi-scale simple attention (MSA) block, which extracts deep semantic ...