DAFE-Net: Direction-Aware Feature Enhancement Network for SAR Ship Detection
Junjie Zeng, Xinxin TANG, Shuang long Li · Remote Sensing · 2026
Synthetic Aperture Radar (SAR) ship detection is important for maritime surveillance and maritime security. However, existing methods still suffer from insufficient backbone representation, inadequate directional structure modeling, and limited cross-scale interaction under complex backgrounds. To address these issues, we propose a Direction-Aware Feature Enhancement Network (DAFE-Net). First, a Multi-Branch Feature Interaction Module (MBFIM) is designed to improve the collaborative representation of global structures and local details. Second, a Direction-Aware Contrast Enhancement Module (DACEM) is introduced to explicitly model the directional bright–dark coupled structures of SAR ships, thereby improving target–background discrimination under complex clutter. Finally, a Feature-Focused Diffusion Pyramid Network (FFDPN) is constructed to strengthen cross-scale feature interaction and improve the detection of multi-scale ship targets. Experimental results show that the proposed method outperforms several competitive detectors on the merged SSDD and HRSID dataset. Compared with DEIM-D-FINE, our method improves AP by 3.1% and APL by 5.0%. These results demonstrate that the proposed method provides an effective direction-aware modeling approach for SAR ship detection.