A Mask Attention Interaction and Scale Enhancement Network for SAR Ship Instance Segmentation

Most of the existing synthetic aperture radar (SAR) ship instance segmentation models do not achieve mask interaction or offer limited interaction performance. Besides, their multiscale ship instance segmentation performance is moderate especially for small ships. To solve these problems, we propose a mask attention interaction and scale enhancement network (MAI-SE-Net) for SAR ship instance segmentation. MAI uses an atrous spatial pyramid pooling (ASPP) to gain multiresolution feature responses, a nonlocal block (NLB) to model long-range spatial dependencies, and a concatenation shuffle attention block (CSAB) to improve interaction benefits. SE uses a content-aware reassembly of features block (CARAFEB) to generate an extra pyramid bottom level to boost small ship performance, a feature balance operation (FBO) to improve scale feature description, and a global context block (GCB) to refine features. Experimental results on two public SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Images Dataset (HRSID) datasets reveal that MAI-SE-Net outperforms the other nine competitive models, better than the suboptimal model by 4.7% detection average precision (AP) and 3.4% segmentation AP on SSDD and by 3.0% detection AP and 2.4% segmentation AP on HRSID.