Statistic Ratio Attention-Guided Siamese U-Net for SAR Image Semantic Change Detection

Semantic change detection (SCD), which aims to locate land cover changes and identify their categories using pixel-level boundaries, has promising applications in Earth vision, including precise urban planning and natural resource management. This letter proposes a novel Siamese U-Net architecture for SCD in synthetic aperture radar (SAR) images, incorporating a residual network with weight-sharing as the backbone network. The network is capable of simultaneously yielding binary change detection (CD) and SCD results. Additionally, we have designed a statistic ratio attention module that utilizes statistical features from the original image as spatial ratio attention, coupled with channel attention, to extract change information from the bi-temporal SAR images. Furthermore, as there is currently no existing dataset for SCD in SAR images, we have constructed a dedicated dataset to facilitate model training and evaluation. Our experiment results demonstrate the superiority of our proposed model over other comparison algorithms.