Cross-Scale Feature Propagation Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Over the past few years, various strategies have been proposed to improve the multiscale information capture capability of networks, such as encoder-decoder framework, convolution layers with different kernel sizes in parallel, and multiple branches framework. However, many methods only rely on one of the strategies, which limits their performance when processing remote sensing images (RSIs) with large-scale variance. To address this issue and enable the fast and effective extraction of multiscale semantic information, this manuscript introduces a novel cross-scale feature propagation network (CFPNet). Specifically, the multiscale convolution (MSC) module aims to capture fine-grained multiscale context with different receptive fields, and the attention upsample (AUS) module embeds the semantic information of high-level features into low-level features while maintaining spatial details. Besides, the feature semantic enhancement (FSE) module is proposed to aggregate the multilayer features of the decoder to enhance the final feature representation. The experimental results on the Beijing Land-Use (BLU) and GID datasets demonstrate the effectiveness and efficiency of our CFPNet.