D²ADet: dual-activation domain RetinaNet based on a deformable feature pyramid network for ship detection in SAR images

ABSTRACT

RetinaNet has been widely used in the field of ship detection in synthetic aperture radar (SAR) images due to its simple structure and excellent performance. Although various modified RetinaNet models for SAR ship detection have been proposed, there are still some problems, such as how to capture more complete ship features and the unbalanced distribution of positive samples in different tasks, which have not been mentioned in previous studies. Aiming at the above problems, this paper proposes a modified RetinaNet detector for SAR ship detection, namely D${ }^2$ADet. Specifically, a modified feature pyramid network is proposed to capture adaptive features that are more suitable for the ship. Then, a dual-activation domain training method is designed to decouple the sample assignment processes of different tasks to meet their requirements of positive samples for each task. Experimental results show that compared with RetinaNet, D${ }^2$ADet obtains 7.67$\mathrm{\%}$, 11.57$\mathrm{\%}$ and 7.28$\mathrm{\%}$ gains in AP50, AP75 and mAP on the public SAR ship detection dataset (SSDD), respectively. And D${ }^2$ADet achieves the state-of-the-art performance compared with other methods.

KEYWORDS:

• SAR
• ship detection
• RetinaNet
• feature pyramid network
• sample assignment

Disclosure statement

No potential conflict of interest was reported by the author(s).