Gabor-Modulated Grouped Separable Convolutional Network for Hyperspectral Image Classification

Abstract

Nowadays, convolutional neural network (CNN)-based deep learning (DL) models have been popularized in hyperspectral image classification (HSIC) and achieved significant accuracy gains, which is due to their hierarchical and nonlinear feature learning patterns. However, too deeper network structures may induce a huge amount of parameters and excessive computing overhead, leading to the need for plenty of labeled samples for training. Besides, highly abstract semantic features may not be the most suitable for hyperspectral land-cover classification tasks. To address these issues, we propose a fairly lightweight network model for HSIC, which is built on a type of exquisitely designed convolution module, namely, grouped separable convolution (GSC). Compared with the standard convolution, the designed GSC module combines grouped convolution with pointwise convolution, which not only greatly reduces the number of parameters of convolution kernels but also caters to the inherent 3-D cube style of hyperspectral image (HSI) data. Moreover, Gabor filters are introduced to modulate the GSC kernels, so as to further use relatively few convolution kernels with additional prior orientation and scale information for feature extraction. The experiments are carried out on four real hyperspectral datasets, and the experimental results reveal that the proposed model has low training cost and memory overhead. Compared with some existing deep network models that have been applied to HSIC, our proposed model can achieve competitive classification accuracy with fewer training samples.