Grid Network: Feature Extraction in Anisotropic Perspective for Hyperspectral Image Classification

Zhonghao Chen, Danfeng Hong, Hongmin Gao

Abstract: Abundant spectral signatures and spatial characteristics embedded in hyperspectral (HS) images enable the fine identification of land covers, attracting plenty of studies on feature extraction (FE) and feature utilization. Nevertheless, the high representative spectral and spatial features in the HS cube are unevenly distributed, which is failed to consider by many current methods. To conquer this shortcoming, we rethink the FE of HS images from an anisotropic perspective and propose a novel model called grid network (GNet) for HS image classification (HSIC). Beyond representing spectral–spatial features in three classic paradigms (simultaneously, hierarchically, and separately), GNet is capable of learning them in two new processes: multistage and multipath. In this way, spectral and spatial features can be fully and balanced explored. More significantly, to make full use of low- and high-level features and avoid the existing semantic gap, we devise a spectral–spatial cross-level feature fusion (S2CLF2) module to model the relationship between them. Extensive experiments, implemented on three HS datasets, demonstrate that the proposed GNet enables to acquire promising classification performance compared with state-of-the-art methods. The codes of this work will be available at https://github.com/zhonghaochen/GNet_Master for the sake of reproducibility.