With recent advances in deep-learning techniques and the advantages of synthetic aperture radar (SAR) images, deep-learning-based SAR ship detection has attracted a lot of attention. In this letter, we aim to build an SAR ship detection framework that is robust to target shape variations. Focusing on shape variation caused by radar shadow, we propose an instance-level data augmentation (DA) method. We leverage ground-truth annotations for bounding box and instance segmentation mask to design a sophisticated pipeline to simulate target information loss while preserving contextual information. In order to enhance the capacity to model shape variation, we design network architecture using deformable convolutional networks (DCNs). Furthermore, we introduce contrastive region of interest (RoI) loss to encourage similarity between original and augmented target RoI features, while encouraging background features to be distinguished from the target RoI features. We present extensive experiments to demonstrate the effectiveness of the proposed method.
|Journal||IEEE Geoscience and Remote Sensing Letters|
|Publication status||Published - 2022|
Bibliographical noteFunding Information:
This work was supported by the Agency for Defense Development under Grant UD2000008RD.
© 2004-2012 IEEE.
All Science Journal Classification (ASJC) codes
- Geotechnical Engineering and Engineering Geology
- Electrical and Electronic Engineering