Local–Global Gated Convolutional Neural Network for Hyperspectral Image Classification

How to learn the most valuable and useful features in convolutional neural networks (CNNs) is the key for accurate hyperspectral image classification (HSIC). Focused on this issue, we developed a local–global gated CNN (LGG-CNN), in this letter. The core is the simultaneous construction of local and global gated convolution blocks, with the aim to select highly discriminative information and filtering redundant information in hyperspectral images (HSIs). Different from traditional CNN methods treating all spectral–spatial features equally, the gated convolutions help in learning a normalized soft mask to guide the network to focus on valid features and neglect the invalid ones. Here, based on the CNN backbone, multilayer local features are first learned via gated convolutional architecture, which mainly consists of convolution operators and nonlinearly activation functions. At the same time, a global gated block (GGB) is designed to conduct feature serialization-mapping-patching operations, to learn global features from deeper layers with larger receptive fields. As a result, the local/GGBs can dynamically learn discriminative feature selection mechanisms for each channel at each spatial location. Then, the local and global features are fused at both the feature-level and decision-level. In this manner, the effective fusion of features by the multilayer LGG convolution blocks enables spatial interaction across layers, leading to further improvement in classification accuracy. Extensive experiments on three benchmark HSIC datasets demonstrate the superiority of LGG-CNN over some state-of-the-art methods. The source code of the proposed method is available at https://github.com/Ding-Kexin/LGG-CNN .