AMANet: Advancing SAR Ship Detection With Adaptive Multi-Hierarchical Attention Network

Synthetic Aperture Radar (SAR) ship detection is crucial for maritime surveillance, environmental monitoring, and national security. Recently, methods based on deep learning have been successfully applied to ship detection for SAR images. Despite the development of numerous ship detection methodologies, detecting small and coastal ships remains a significant challenge due to the limited features and clutter in coastal environments. For that, a novel adaptive multi-hierarchical attention module (AMAM) is proposed to learn multi-scale features and adaptively aggregate salient features from various feature layers, even in complex environments. Specifically, we first fuse information from adjacent feature layers to enhance the detection of smaller targets, thereby achieving multi-scale feature enhancement. Then, to filter out the adverse effects of complex backgrounds, we dissect the previously fused multi-level features on the channel, individually excavate the salient regions, and adaptively amalgamate features originating from different channels. Thirdly, we present a novel adaptive multi-hierarchical attention network (AMANet) by embedding the AMAM between the backbone and the feature pyramid network (FPN). Besides, the AMAM can be readily inserted between different frameworks to improve object detection. Lastly, extensive experiments on two large-scale SAR ship detection datasets, namely the SSDD and HRSID, demonstrate that our AMANet method achieves superior performance over state-of-the-art methods, with an AP of 74.20% and 68.90% on the SSDD and HRSID datasets, respectively.