Adaptive feature alignment network with noise suppression for cross-domain object detection

IF 5.5 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Neurocomputing Pub Date : 2024-10-28 DOI:10.1016/j.neucom.2024.128789
Wei Jiang , Yujie Luan , Kewei Tang , Lijun Wang , Nan Zhang , Huiling Chen , Heng Qi
{"title":"Adaptive feature alignment network with noise suppression for cross-domain object detection","authors":"Wei Jiang ,&nbsp;Yujie Luan ,&nbsp;Kewei Tang ,&nbsp;Lijun Wang ,&nbsp;Nan Zhang ,&nbsp;Huiling Chen ,&nbsp;Heng Qi","doi":"10.1016/j.neucom.2024.128789","DOIUrl":null,"url":null,"abstract":"<div><div>Recently, unsupervised domain adaptive object detection methods have been proposed to address the challenge of detecting objects across different domains without labeled data in the target domain. These methods focus on aligning features either at the image level or the instance level. However, due to the absence of annotations in the target domain, existing approaches encounter challenges such as background noise at the image level and prototype aggregation noise at the instance level. To tackle these issues, we introduce a novel adaptive feature alignment network for cross-domain object detection, comprising two key modules. Firstly, we present an adaptive foreground-aware attention module equipped with a set of learnable part prototypes for image-level alignment. This module dynamically generates foreground attention maps, enabling the model to prioritize foreground features, thus reducing the impact of background noise. Secondly, we propose a class-aware prototype alignment module incorporating an optimal transport algorithm for instance-level alignment. This module mitigates the adverse effects of region–prototype aggregation noise by aligning prototypes with instances based on their semantic similarities. By integrating these two modules, our approach achieves better image-level and instance-level feature alignment. Extensive experiments across three challenging scenarios demonstrate the effectiveness of our method, outperforming state-of-the-art approaches in terms of object detection performance.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":null,"pages":null},"PeriodicalIF":5.5000,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neurocomputing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0925231224015601","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Recently, unsupervised domain adaptive object detection methods have been proposed to address the challenge of detecting objects across different domains without labeled data in the target domain. These methods focus on aligning features either at the image level or the instance level. However, due to the absence of annotations in the target domain, existing approaches encounter challenges such as background noise at the image level and prototype aggregation noise at the instance level. To tackle these issues, we introduce a novel adaptive feature alignment network for cross-domain object detection, comprising two key modules. Firstly, we present an adaptive foreground-aware attention module equipped with a set of learnable part prototypes for image-level alignment. This module dynamically generates foreground attention maps, enabling the model to prioritize foreground features, thus reducing the impact of background noise. Secondly, we propose a class-aware prototype alignment module incorporating an optimal transport algorithm for instance-level alignment. This module mitigates the adverse effects of region–prototype aggregation noise by aligning prototypes with instances based on their semantic similarities. By integrating these two modules, our approach achieves better image-level and instance-level feature alignment. Extensive experiments across three challenging scenarios demonstrate the effectiveness of our method, outperforming state-of-the-art approaches in terms of object detection performance.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
具有噪声抑制功能的自适应特征对齐网络,用于跨域物体检测
最近,有人提出了无监督领域自适应物体检测方法,以应对在目标领域没有标记数据的情况下跨不同领域检测物体的挑战。这些方法的重点是在图像层或实例层对齐特征。然而,由于目标域中没有注释,现有方法会遇到一些挑战,如图像级的背景噪声和实例级的原型聚合噪声。为了解决这些问题,我们引入了一种用于跨域对象检测的新型自适应特征对齐网络,该网络由两个关键模块组成。首先,我们提出了一个自适应前景感知注意力模块,该模块配备了一套可学习的部件原型,用于图像级对齐。该模块可动态生成前景注意图,使模型能够优先考虑前景特征,从而降低背景噪声的影响。其次,我们提出了一种类感知原型对齐模块,其中包含一种用于实例级对齐的优化传输算法。该模块根据语义相似性将原型与实例对齐,从而减轻了区域原型聚合噪声的不利影响。通过整合这两个模块,我们的方法实现了更好的图像级和实例级特征配准。在三个具有挑战性的场景中进行的广泛实验证明了我们方法的有效性,在物体检测性能方面优于最先进的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Neurocomputing
Neurocomputing 工程技术-计算机:人工智能
CiteScore
13.10
自引率
10.00%
发文量
1382
审稿时长
70 days
期刊介绍: Neurocomputing publishes articles describing recent fundamental contributions in the field of neurocomputing. Neurocomputing theory, practice and applications are the essential topics being covered.
期刊最新文献
An efficient re-parameterization feature pyramid network on YOLOv8 to the detection of steel surface defect Editorial Board Multi-contrast image clustering via multi-resolution augmentation and momentum-output queues Augmented ELBO regularization for enhanced clustering in variational autoencoders Learning from different perspectives for regret reduction in reinforcement learning: A free energy approach
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1