CGFRNet: A Context-Guided and Feature Refined Network for SAR Image Ship Detection

Synthetic Aperture Radar (SAR)-based remotely sensed imagery plays a crucial role in both civil and military domains. However, complex background interference, dense distribution, and different ship sizes are the current interrelated and unsolvable challenges. To this end, we propose a context-guided and feature refinement network (CGFRNet) for ship detection in SAR images. First, a feature refinement module (FRM) is designed to capture spatial contextual information of targets at different scales while suppressing easily confused background interference. Second, the context-guided attention module (CGAM) is introduced to fully integrate the shallow feature mapping with the deeper layers further to enhance the focusing and extraction of key features of the ship. Third, due to the dense distribution of most small ships in SAR images, the separation enhanced attention module (SEAM) is incorporated into the detection head to learn the dependencies between features and dynamically adjust the attention points in the feature maps to enhance the model performance in dense target scenes. Experimental results on HRSID, SSDD, and LS-SSDD-v1.0 datasets show that the proposed method can significantly improve the detection accuracy of multi-scale targets in complex scenes and achieve a more advanced performance.