雷达科学与技术2024，Vol.22Issue(1)：14-20,7.DOI:10.3969/j.issn.1672-2337.2024.01.003
用于SAR图像舰船目标检测的MAF-Net和CS损失
A Multi-Scale Attention Fusion Network and Cosine Similar Loss for SAR Ship Detection
摘要
Abstract
Deep learning algorithms are widely used in the field of synthetic aperture radar(SAR)image ship de-tection for their advantages of end-to-end training and high accuracy.However,ship targets in SAR images span a large size and are susceptible to the interference from complex backgrounds and noise,which affects the detection accuracy.To further improve the detection accuracy of the network,a multi-scale attention fusion network(MAF-Net)is proposed in this paper.The network mainly contains a multi-scale feature attention fusion(MFAF)module,which uses the fea-ture maps output from the backbone network,fuses the multi-scale information,and enhances the feature maps output from the FPN in the spatial and channel dimensions.In this way,the influence of noise and background on the ship tar-get is suppressed and the feature extraction capability of the network is enhanced.In addition,a cosine similar(CS)loss is proposed,which enables the network to more accurately distinguish the ship target from the background by calcu-lating the cosine similarity between the target and non-target regions,to further improve the accuracy.Numerous experi-ments show that the proposed methods have higher detection accuracy compared with several existing algorithms on SS-DD and SAR-Ship-Dataset datasets.关键词
目标检测/深度学习/SAR图像/多尺度注意力融合网络/余弦相似损失Key words
target detection/deep learning/synthetic aperture radar(SAR)image/multi-scale attention fusion network/cosine similar(CS)loss分类
信息技术与安全科学引用本文复制引用
张丽丽,蔡健楠,刘雨轩,屈乐乐..用于SAR图像舰船目标检测的MAF-Net和CS损失[J].雷达科学与技术,2024,22(1):14-20,7.基金项目
辽宁省兴辽英才计划项目基金(No.XLYC1907134) （No.XLYC1907134）
辽宁省教育厅项目(No.LJKZ0174) （No.LJKZ0174）
