Semisupervised Variational Generative Adversarial Networks for Hyperspectral Image Classification

Abstract

Although the hyperspectral image (HSI) classification is extensively investigated, this task remains challenging when the number of labeled samples is extremely limited. In this article, we overcome this challenge by using synthetic samples and proposing semisupervised variational generative adversarial networks (GANs). In contrast to conditional GAN (previously used for the generation of HSI samples), the proposed approach has two novel aspects. First, an encoder-decoder network is extended to the semisupervised context using an ensemble prediction technique. Through this technique, our deep generative model can be trained using limited labeled samples (only five samples per class) with a large number of unlabeled samples. Second, we build a collaborative relationship between the generation network and the classification network. This property enables that our model can produce meaningful samples that can contribute to the final classification. The experiments on four benchmark HSI datasets demonstrate that the proposed model can achieve an increase of >10% in overall classification accuracy compared with the baseline model without using the generated sample. We also show that the proposed model can achieve better and more robust performance for HSI classification than other generative methods as well as semisupervised methods, especially when the labeled data are limited.