A Weak Supervision Learning Paradigm for Oriented Ship Detection in SAR Image

The advancement of convolutional neural networks (CNNs) has greatly promoted the development of ship detection in SAR images. Oriented ship detection is practical and imperative, but the development of its fully-supervised methods is limited by the insufficiency of data annotated in an oriented bounding box (OBB). Therefore, we proposed a weakly supervised learning (WSL) paradigm to train the network by only data annotated in a horizontal bounding box (HBB) for oriented ship detection. The paradigm follows a coarse-to-fine prediction route, and the ships’ coarse orientations and high-quality pseudolabels both mined from images are used to train the network combined with the HBB annotations. The designed orientation initialization decoder (OID) utilizes the output from the prediction branch of ship coarse orientation (PBSCO) and the regression branch to decode coarse OBBs, based on the horizontal proposals, and then these OBBs are refined by the fine prediction head, which is jointly trained by high-quality pseudolabels and HBB annotation. Extensive experiments were conducted on the SAR ship detection dataset (SSDD) and the high-resolution SAR images dataset (HRSID) with both OBB and HBB annotations, and the results show that our proposed WSL paradigm can train network to attain the
$AP_{50}$
and R in the same level of mainstream fully-supervised methods in remote sensing.