Adaptive Spectral and Spatial Feature Extraction Framework for Hyperspectral Classification

Hyperspectral image (HSI) classification is an important research topic in the field of remote sensing. In addition to discriminative spectral information, spatial information also plays an important part in HSI data. So jointly extracting spectral-spatial features is popular to achieve better classification in most recent research. However, simply directly introducing the spatial information without analyzing its necessity will result in some problems. In some cases, spectra have enough material discrimination ability and spatial feature is indeed unneceseary which will brings additional computational burden and even adversely affect the classification results. In order to address these problems, we propose an adaptive spectral spatial feature extraction framework with early prediction strategy for HSI classification. Our method can not only perform high efficiency but also reduce the potential interference of spatial information to improve classification accuracy. Specifically, it mainly consists of two classification branches and a small gate network which is utilized to adaptively determine the necessity of spatial features. Experimental results on the public HSI datasets demonstrate that our approach obtains better performance in both accuracy and efficiency than the comparative state-of-the-art level methods.