Synergistic Attention for Ship Instance Segmentation in SAR Images

• Published in: Remote sensing (Basel, Switzerland) Vol. 13; no. 21; p. 4384
• Main Authors: Zhao, Danpei, Zhu, Chunbo, Qi, Jing, Qi, Xinhu, Su, Zhenhua, Shi, Zhenwei
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.11.2021
• Subjects: Algorithms; Datasets; Deep learning; Feature extraction; feature fusion; Image processing; Image segmentation; Instance segmentation; Methods; Modules; Neural networks; Radar imaging; Remote sensing; SAR images; Semantics; ship instance segmentation; synergistic attention; Synthetic aperture radar
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs13214384

This paper takes account of the fact that there is a lack of consideration for imaging methods and target characteristics of synthetic aperture radar (SAR) images among existing instance segmentation methods designed for optical images. Thus, we propose a method for SAR ship instance segmentation based on the synergistic attention mechanism which not only improves the performance of ship detection with multi-task branches but also provides pixel-level contours for subsequent applications such as orientation or category determination. The proposed method—SA R-CNN—presents a synergistic attention strategy at the image, semantic, and target level with the following module corresponding to the different stages in the whole process of the instance segmentation framework. The global attention module (GAM), semantic attention module (SAM), and anchor attention module (AAM) were constructed for feature extraction, feature fusion, and target location, respectively, for multi-scale ship targets under complex background conditions. Compared with several state-of-the-art methods, our method reached 68.7 AP in detection and 56.5 AP in segmentation on the HRSID dataset, and showed 91.5 AP in the detection task on the SSDD dataset.