Abstract
Band selection (BS) aims to reduce redundancy in hyperspectral imagery (HSI). Existing BS approaches typically model HSI only in a single dimension, either spectral or spatial, without exploring the interactions between different dimensions. To this end, we propose an unsupervised BS method based on a spectral–spatial cross-dimensional attention network, named SSANet-BS. This network is comprised of three stages: a band attention module (BAM) that employs an attention mechanism to adaptively identify and select highly significant bands; two parallel spectral–spatial attention modules (SSAMs), which fuse complex spectral–spatial structural information across dimensions in HSI; a multi-scale reconstruction network that learns spectral–spatial nonlinear dependencies in the SSAM-fusion image at various scales and guides the BAM weights to automatically converge to the target bands via backpropagation. The three-stage structure of SSANet-BS enables the BAM weights to fully represent the saliency of the bands, thereby valuable bands are obtained automatically. Experimental results on four real hyperspectral datasets demonstrate the effectiveness of SSANet-BS.
Funding Information
  • Qingdao Natural Science Foundation (23-2-1-64-zyyd-jch, 2023M731843, QDBSH20230101012, 42301380, 2023KJ232)
  • China Postdoctoral Science Foundation (23-2-1-64-zyyd-jch, 2023M731843, QDBSH20230101012, 42301380, 2023KJ232)
  • Postdoctoral Applied Research Foundation of Qingdao (23-2-1-64-zyyd-jch, 2023M731843, QDBSH20230101012, 42301380, 2023KJ232)
  • National Natural Science Foundation of China (23-2-1-64-zyyd-jch, 2023M731843, QDBSH20230101012, 42301380, 2023KJ232)
  • Science and Technology Support Plan for Youth Innovation of Colleges and Universities of Shandong Province of China (23-2-1-64-zyyd-jch, 2023M731843, QDBSH20230101012, 42301380, 2023KJ232)

This publication has 49 references indexed in Scilit: