Litcius/Paper detail

Joint Spatial–Spectral Attention Network for Hyperspectral Image Classification

Lei Li, Jihao Yin, Xiuping Jia, Sen Li, Bingnan Han

2020IEEE Geoscience and Remote Sensing Letters30 citationsDOI

Abstract

Hyperspectral images (HSIs) contain rich context information in the spatial domain and spectral domain. To fully explore that information, a data-driven joint spatial–spectral attention network (JSSAN) is proposed in this letter. Specifically, we first design a spatial–spectral attention ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{S}^{2}\text{A}$ </tex-math></inline-formula> ) block to simultaneously capture long-range interdependency of spatial and spectral data via the similarity evaluation. Then we adopt a weighted sum operation of features at all spatial positions and channels to selectively aggregate discriminative spatial–spectral features. Second, the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\text{S}^{2}\text{A}$ </tex-math></inline-formula> block is inserted into simple convolutional neural network (CNN) structure to extract more representative features for classification, by adaptively emphasizing features of informative land covers and spectral bands which contribute more to class identification. The experimental results reveal that our proposed method outperforms several state-of-the-art algorithms.

Topics & Concepts

Hyperspectral imagingDiscriminative modelPattern recognition (psychology)Artificial intelligenceComputer scienceConvolutional neural networkSpatial analysisContext (archaeology)Block (permutation group theory)MathematicsCombinatoricsStatisticsBiologyPaleontologyRemote-Sensing Image ClassificationRemote Sensing and Land UseLand Use and Ecosystem Services
Joint Spatial–Spectral Attention Network for Hyperspectral Image Classification | Litcius