Hyperspectral Imagery Classification Based on Compressed Convolutional Neural Network

Abstract

Deep neural networks have achieved excellent performance in computer vision and many other fields. However, this good result is at the cost of high model complexity and expensive hardware requirement. Hence, it is an important topic to keep the performance of the deep model with as few parameters as possible. Inspired by the knowledge distillation (KD) method, a hyperspectral imagery (HSI) classification method based on compressed neural network is proposed in this letter. Different from the original KD method, virtual samples are adopted to describe the classification boundary of the teacher network more accurately, which effectively improves the classification accuracy of the student network. Experimental results of three real HSI data sets show that the superiority of the proposed method to the state-of-the-art algorithms in terms of classification accuracy and model complexity.