**6. Conclusions**

In this paper, GCBANet is proposed for better SAR ship instance segmentation. In GCBANet, GCIM-Block and BABP-Block are designed to ensure its excellent performance. Specifically, GCIM-Block is used to mitigate the inferences caused by the surroundings of ships and the mechanism of SAR imaging. BABP-Block is used to locate ships more precisely. Ablation studies can confirm the effectiveness of GCIM-Block and BABP-Block. The results on two open datasets reveal the state-of-the-art performance of GCBANet compared to the other nine competitive models. On SSDD, GCBANet achieves 2.8% higher box AP and 3.5% higher mask AP than the existing best model; on HRSID, they are 2.7% and 1.9%.

Our future work is as follows:


**Author Contributions:** Conceptualization, T.Z.; methodology, X.K.; software, X.K.; validation, T.Z.; formal analysis, T.Z.; investigation, T.Z.; resources, T.Z.; data curation, T.Z.; writing—original draft preparation, X.K. and T.Z.; writing—review and editing, X.K. and T.Z.; visualization, T.Z.; supervision, X.K.; project administration, X.Z.; funding acquisition, X.Z. All authors have read and agreed to the published version of the manuscript.

**Funding:** This work was supported by the National Natural Science Foundation of China (61571099).

**Data Availability Statement:** Not applicable.

**Acknowledgments:** The authors would like to thank the editors and the four anonymous reviewers for their valuable comments that can greatly improve our manuscript.

**Conflicts of Interest:** The authors declare that they have no conflicts of interest.
