YOLO-SR: An optimized convolutional architecture for robust ship detection in SAR Imagery

• A novel one-stage SAR ship detection model, YOLO-SR, is designed to handle speckle noise and large-scale variations while maintaining computational efficiency. • A Balanced Detail Fusion module enhances the integration of fine-grained shallow features with deeper semantic features, improving the detection of small and low-contrast ships. • The C2f-MSDR backbone incorporates Multi-Scale Dilation Residual blocks to expand the receptive field, effectively capturing ships of varying sizes in complex SAR environments. • A data-driven upsampling strategy preserves spatial fidelity, mitigating boundary artifacts and enhancing vessel contour resolution. • A specialized bounding-box regression loss function integrates orientation, distance, and scale factors with a focal mechanism for better detection of occluded ships. • Comprehensive experiments on SAR ship detection dataset demonstrate YOLO-SR’s superiority over state-of-the-art methods, particularly in detecting small and cluttered targets. Accurate and efficient ship detection in synthetic aperture radar (SAR) imagery remains a challenging task due to speckle noise, scale variations, and the low contrast of small vessels. In this work, we present YOLO-SR, an enhanced version of YOLOv10 tailored for SAR ship detection, introducing four key innovations: Balanced Detail Fusion (BDF), C2f‐MSDR, DySample, and the Focaler-SIoU loss. Our BDF module adaptively merges shallow, fine‐grained features with deeper semantic features, preventing subtle ship signatures from being overshadowed by irrelevant clutter. Concurrently, C2f‐MSDR replaces standard bottleneck layers with multi-scale dilation residual blocks, expanding the receptive field to handle wide variations in ship size. To improve spatial resolution and retain boundary details, we incorporate DySample, a data-driven upsampling strategy that counteracts the artifacts of naive interpolation. Finally, Focaler-SIoU refines bounding-box regression by integrating distance, orientation, shape, and a focal-like reweighting, thereby emphasizing difficult, small, or partially occluded ships. Experimental results on SAR ship detection datasets confirm that YOLO-SR outperforms state-of-the-art methods in both precision and recall, while retaining competitive inference speeds. These advances offer a robust framework for real-time maritime surveillance, enhancing the detection of both small and large ships under challenging SAR conditions.