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

TL;DR

This paper introduces AMANet, a novel deep learning framework with an adaptive multi-hierarchical attention module designed to improve SAR ship detection, especially for small and coastal ships in complex environments.

Contribution

The paper proposes a new adaptive multi-hierarchical attention module (AMAM) and integrates it into AMANet to enhance multi-scale feature learning and saliency detection in SAR images.

Findings

AMANet outperforms existing methods on large-scale SAR datasets.

The adaptive multi-hierarchical attention module improves small and coastal ship detection.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Recently, methods based on deep learning have been successfully applied to ship detection for synthetic aperture radar (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 network 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 demonstrate that our AMANet method is superior to state-of-the-art methods.