Small Object Detection in Synthetic Aperture Radar with Modular Feature Encoding and Vectorized Box Regression

Object detection in synthetic aperture radar (SAR) imagery poses significant challenges due to low resolution, small objects, arbitrary orientations, and complex backgrounds. Standard object detectors often fail to capture sufficient semantic and geometric cues for such tiny targets. To address this issue, a new Convolutional Neural Network (CNN) framework called Deformable Vectorized Detection Network (DVDNet) has been pro-posed, specifically designed for detecting small, oriented, and densely packed objects in SAR images. The DVDNet consists of Grouped-Deformable Convolution for adaptive receptive field adjustment to diverse object scales, a Local Binary Pattern (LBP) En-hancement Module that enriches texture representations and enhances the visibility of small or camouflaged objects, and a Vector Decomposition Module that enables accurate regression of oriented bounding boxes via learnable geometric vectors. The DVDNet is embedded in a two-stage detection architecture and is particularly effective in preserving fine-grained features critical for small object localization. The performance of DVDNet is validated on two SAR small target detection datasets, HRSID and SSDD, and it is ex-perimentally demonstrated that it achieves 90.9% mAP on HRSID and 87.2% mAP on SSDD. The generalizability of DVDNet was also verified on the remote sensing dataset Pascal VOC 2012 and the generalized dataset HRSC2016. All these experiments show that DVDNet outperforms the standard detector. Notably, our framework shows substantial gains in precision and recall for small object subsets, validating the importance of com-bining deformable sampling, texture enhancement, and vector-based box representation for high-fidelity small object detection in complex SAR scenes.