A Two-Stage Convolutional Sparse Coding Network for Hyperspectral Image Classification

Abstract

The convolutional sparse coding (CSC) can learn shift-invariant convolution kernels. In deep convolutional neural networks, it needs take a lot of time to train the convolution kernels. In this letter, a deep two-stage convolutional sparse coding network (DTCSCNet) is proposed, which can be used to simultaneously extract spatial features and spectral features from hyperspectral image (HSI) without back propagation and fine-tuning process, and thus saving a lot of time. Furthermore, to further improve the performance of the network, we incorporate multi-scale information. After deep feature extraction using DTCSCNet, we further investigate the classification performance of different classifiers on the extracted features. Experimental results show that the proposed method can obtain better classification performance compared with some closely related HSI classification methods.