Neural Stochastic Differential Equation for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is an essental task of HSI analysis, which aims to assign each pixel a pre-defined class label. Though deep learning based methods dominate the HSI classification methods to date, the existing methods seldom consider how to directly model the uncertainty broadly exists in the HSI applications, which impedes their usage in real applications. To address this problem, we propose to directly model the uncertainty into the deep learning based HSI classification model and construct a specific network based on stochastic differential equation (SDE). The constructed network consists two subnets, in which one is utilized to well fit the HSI classification task and one is exploited to capture the uncertainty within the HSI classification. The constructed network can better depict the uncertainty, and thus result in better HSI classification performance. Experimental results demonstrate the effectiveness of the constructed model for HSI classification.