Multi-branch fusion network for hyperspectral image classification

Abstract

Hyperspectral remote sensing image (HSI) has the characteristics of large data volume and high spectral resolution. It contains abundant spectral information and has tremendous applicable value. Convolutional neural network (CNN) has been successfully applied to HSI classification. However, the limited labeled samples of the HSI make the existing CNN based HSI classification methods generally be plagued by small sample size problem and class imbalance, which cause great challenges for HSI classification. This work proposes a novel CNN architecture for HSI classification. The proposed CNN is a multi-branch fusion network, which is formed by merging multiple branches on an ordinary CNN. It can effectively extract features of HSIs. In addition, the 1 × 1 convolutional layer is introduced into the branches to reduce the number of parameters and then improve the classification efficiency. Furthermore, the L2 regularization is introduced into this work to improve the generalization performance of the proposed model under small sample set. Experimental results on three benchmark hyperspectral images demonstrate that the proposed CNN can provide excellent classification performance under small training set.