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.

Due to the redundancy and sparsity of hyperspectral data, sparse representation (SR) has proven to be well-suited for hyperspectral band selection (BS). Moreover, graph regularizers can effectively incorporate local structural information of the data to improve the solution of SR. However, existing unsupervised BS approaches typically consider only a simple graph based on a single spectral metric. In contrast, the hypergraph can capture the multiple adjacencies of the bands and has significant advantages. This letter proposes a hypergraph-regularized self-representation model (HyGSR) for BS. HyGSR is innovative in that it jointly combines the spectral similarity and band index as a new similarity metric to rationalize the local structure of bands extracted by hypergraph, while using a robust l _2,1 -norm to exploit the sparse properties of the data for BS. Experimental results on four real hyperspectral scenarios verify that HyGSR outperforms other competitors with high stability and usability.

Band selection (BS) identifies key bands from hyperspectral imagery (HSI) for specific downstream tasks, playing a pivotal role in practical applications. eXtreme Gradient Boosting (XGBoost), an interpretable tree-based ensemble learning classifier, explicitly implements the complex nonlinear hyperspectral classification. The interpretable information extracted from the tree structure offers a novel basis for supervised BS. To this end, this article proposes a supervised BS method, named classification task-driven hyperspectral BS via interpretability from XGBoost (XGBS). It leverages prior knowledge to train a classification task-driven XGBoost and interprets the tree structure to extract multivariate interpretable information, encompassing band split gain and two types of band dependencies. Subsequently, a heuristic search framework is employed to evaluate band performance, facilitating the selection of bands with strong classification capability, high interdependency, and low redundancy. Experiments conducted on six real HSI datasets demonstrate the effectiveness and stability of the proposed XGBS.