Statistical Texture Awareness Network for Hyperspectral Image Classification

The distribution of ground objects in hyperspectral images predominantly reveals spatial indications of both order and disorder, encapsulating a wealth of texture information. This texture information encompasses not only local structural details but also global statistical priors of an image. Nevertheless, convolutional-neural-network-based methods for hyperspectral image classification (HIC) primarily use skip connections to incorporate shallow features abundant in texture information into deeper layers. They face challenges in effectively capturing the statistical properties of texture information, and the traditional method of modeling statistical attributes struggles to seamlessly integrate into parameter learning of convolutional neural networks (CNNs). To do so, this work proposes a statistical texture awareness network (STANet) for HIC. It achieves the exploration of learnable texture features. Through multilevel quantization and quantization encoding, a statistical texture learning module (STLM) is constructed to represent texture information from low-level features in a statistical manner. As a result, it augments the discriminatory power of such features. In addition, a complete feature fusion module (CFFM) is designed to intelligently combine multiscale contextual semantic and statistical texture features, thereby bolstering the discrimination of spectral-spatial ones. Experimental results reported for three public datasets demonstrate the superior performance of the proposed network over other peers.