FCDNet: A Change Detection Network Based on Full-Scale Skip Connections and Coordinate Attention

Abstract

Change detection (CD) is an important means to monitor environmental changes on Earth. Recently, many methods based on deep learning have been proposed for CD tasks. However, existing CD methods still have difficulties in the detection of changing target edges and small changing targets. In this letter, we propose a novel CD method named FCDNet based on full-scale skip connections (FSC) and coordinate attention (CA). FCDNet makes full use of shallow information and high-level semantics through FSC between different levels of encoder features and decoder features, which can effectively alleviate the missed detection of small targets in the CD task. In addition, we design a multi-receptive field position enhancement module (MRPEM) based on CA. MRPEM enhances the local relationship of features through convolution operations of different kernel sizes, and establishes long-distance dependency of features with the application of CA, thus facilitate accurate detection of the edges of changing targets. We also introduce Depthwise Over-parameterized Convolutional Layer (DOConv) in our network architecture, which can improve model performance without increasing computational complexity during inference. The experimental results show that our method is comparable to state-of-the-art (SOTA) methods on the Season-Varying Change Detection (SVCD) dataset.