基于GPA+CBAM的域自适应水下目标检测方法  

Domain-Adaptive Underwater Target Detection Method Based on GPA+CBAM

作　　者：刘麒东 沈鑫 刘海路 丛璐 付先平[1,2] LIU Qidong;SHEN Xin;LIU Hailu;CONG Lu;FU Xianping(The School of Information Science and Technology,Dalian Maritime University,Dalian 116026,China;The Peng ChengLaboratory,Shenzhen 518000,China)

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026 [2]鹏城实验室,广东深圳518000

出　　处：《水下无人系统学报》2024年第5期846-854,共9页Journal of Unmanned Undersea Systems

基　　金：国家自然科学基金项目(62002043、62176037);辽宁省振兴人才计划项目(XLYC1908007);辽宁省重点研发计划项目(201801728);大连市科技创新基金项目(2021JJ12GX028、2019J11CY001、2018J12GX037)。

摘　　要：针对水下目标检测易出现域偏移而导致检测精度下降的现象,文中提出了基于图诱导原型对齐(GPA)的域自适应水下目标检测方法。该方法通过区域建议之间基于图的信息传播得到图像中的实例级特征,导出每个类别的原型表示用于类别级域对齐,从而聚合水下目标的不同模态信息,以此实现源域和目标域的对齐,减少域偏移带来的影响;同时添加了卷积块注意模块(CBAM),使神经网络能够专注于不同水域分布下的实例级特征。实验结果证明该方法能够有效提高发生域偏移时的检测精度。Underwater target detection is often more susceptible to domain shift and reduced detection accuracy.In responseto this phenomenon,this article proposed a domain-adaptive underwater target detection method based on graph-inducedprototype alignment(GPA).GPA obtained instance-level features in the image through graph-based information propagationbetween region proposals and then derived prototype representations for category-level domain alignment.The aboveoperations could effectively aggregate different modal information of underwater targets,thereby achieving alignment betweenthe source and target domains and reducing the impact of domain shift.In addition,in order to make the neural network focuson instance-level features under different water domain distributions,a convolutional block attention module(CBAM)wasadded.The experimental results have shown that the proposed method can effectively improve detection accuracy duringdomain shift.

关 键 词：水下目标检测 图诱导原型对齐 域自适应 卷积块注意模块 

分 类 号：TJ630.34[兵器科学与技术—武器系统与运用工程] U663[交通运输工程—船舶及航道工程]