Mask-Reconstruction-Based Decoupled Convolution Network for Hyperspectral Imagery Classification

Deep learning has attracted much attention in hyperspectral imagery (HSI) classification. However, most deep learning methods ignore the information loss during spatial-spectral feature extraction, which potentially affects the classification performance. In this article, mask-reconstruction-based decoupled convolution network (MrDCN) is proposed, which includes the decoupled feature extraction module (DFEM) to extract spectral information and spatial information of the target HSI patch, respectively. The reconstruction modules are designed to maintain the feature extraction ability of DFEM and ensure that discriminative information in high-dimensional and low-dimensional features is preserved. MrDCN outperforms the state-of-the-art methods in classification on three datasets of various scenarios, which indicates its effectiveness, and experiments on embedded devices are executed to affirm the efficiency of MrDCN.