Hyperspectral image classification via multi-scale residual attention network

The application of convolutional neural network (CNN) in the field of hyperspectral image (HSI) classification has been pervasive. Since hyperspectral images contain numerous complicated spectral-spatial information, only using a single-channel CNN is difficult to fully extract information from the images. As the increasing number of network layers, the network classification accuracy will decrease, and the number of parameters will increase greatly. In order to avoid the above defects, we propose a multi-scale residual attention network to extract features from HSI more efficiently. In addition, the proposed network lowers the number of parameters by introducing depthwise separable convolution (DSC). Experimental studies on two commonly used hyperspectral image datasets verify that the classification performance of the proposed network outperforms some state-of-the-art networks.