Integrating Gate and Attention Modules for High-Resolution Image Semantic Segmentation

Abstract

Semantic segmentation of high-resolution (HR) remote sensing images achieved great progress by utilizing deep convolutional neural networks (DCNNs) in recent years. However, the decrease of resolution in the feature map of DCNNs brings about the loss of spatial information and thus leads to the blurring of object boundary and misclassification of small objects. In addition, the class imbalance and the high diversity of geographic objects in HR images exacerbate the performance. To deal with the above problems, we proposed an end-to-end DCNN network named GAMNet to balance the contradiction between global semantic information and local details. An integration of attention and gate module (GAM) is specially designed to simultaneously realize multiscale feature extraction and boundary recovery. The integration module can be inserted in an encoder-decoder network with skip connection. Meanwhile, a composite loss function is designed to achieve deep supervision of GAM by adding an auxiliary loss, which can help improve the effectiveness of the integration module. The performance of GAMNet is quantitatively evaluated on the ISPRS 2-D semantic labeling datasets and achieves state-of-the-art performance in comparison with other representative methods.