Anti-Forgetting Adaptation for Unsupervised Person Re-Identification.

Hao Chen, Francois Bremond, Nicu Sebe, Shiliang Zhang
{"title":"Anti-Forgetting Adaptation for Unsupervised Person Re-Identification.","authors":"Hao Chen, Francois Bremond, Nicu Sebe, Shiliang Zhang","doi":"10.1109/TPAMI.2024.3490777","DOIUrl":null,"url":null,"abstract":"<p><p>Regular unsupervised domain adaptive person re-identification (ReID) focuses on adapting a model from a source domain to a fixed target domain. However, an adapted ReID model can hardly retain previously-acquired knowledge and generalize to unseen data. In this paper, we propose a Dual-level Joint Adaptation and Anti-forgetting (DJAA) framework, which incrementally adapts a model to new domains without forgetting source domain and each adapted target domain. We explore the possibility of using prototype and instance-level consistency to mitigate the forgetting during the adaptation. Specifically, we store a small number of representative image samples and corresponding cluster prototypes in a memory buffer, which is updated at each adaptation step. With the buffered images and prototypes, we regularize the image-to-image similarity and image-to-prototype similarity to rehearse old knowledge. After the multi-step adaptation, the model is tested on all seen domains and several unseen domains to validate the generalization ability of our method. Extensive experiments demonstrate that our proposed method significantly improves the anti-forgetting, generalization and backward-compatible ability of an unsupervised person ReID model.</p>","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TPAMI.2024.3490777","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Regular unsupervised domain adaptive person re-identification (ReID) focuses on adapting a model from a source domain to a fixed target domain. However, an adapted ReID model can hardly retain previously-acquired knowledge and generalize to unseen data. In this paper, we propose a Dual-level Joint Adaptation and Anti-forgetting (DJAA) framework, which incrementally adapts a model to new domains without forgetting source domain and each adapted target domain. We explore the possibility of using prototype and instance-level consistency to mitigate the forgetting during the adaptation. Specifically, we store a small number of representative image samples and corresponding cluster prototypes in a memory buffer, which is updated at each adaptation step. With the buffered images and prototypes, we regularize the image-to-image similarity and image-to-prototype similarity to rehearse old knowledge. After the multi-step adaptation, the model is tested on all seen domains and several unseen domains to validate the generalization ability of our method. Extensive experiments demonstrate that our proposed method significantly improves the anti-forgetting, generalization and backward-compatible ability of an unsupervised person ReID model.

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
用于无监督人员再识别的反遗忘适应。
常规的无监督领域自适应人员再识别(ReID)侧重于将模型从源领域调整到固定的目标领域。然而,经过适配的 ReID 模型很难保留以前获得的知识,也很难泛化到未见过的数据。在本文中,我们提出了一种双层联合适配和防遗忘(DJAA)框架,它能在不遗忘源域和每个适配目标域的情况下,将模型逐步适配到新的域。我们探索了使用原型和实例级一致性来减轻适应过程中遗忘的可能性。具体来说,我们将少量具有代表性的图像样本和相应的集群原型存储在内存缓冲区中,并在每个适应步骤中进行更新。利用缓冲区中的图像和原型,我们对图像与图像之间的相似性和图像与原型之间的相似性进行正则化处理,以重新梳理旧知识。经过多步适应后,我们在所有可见领域和多个未见领域对模型进行了测试,以验证我们方法的泛化能力。大量实验证明,我们提出的方法显著提高了无监督人脸识别模型的抗遗忘、泛化和向后兼容能力。
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
自引率
0.00%
发文量
0
期刊最新文献
EBMGC-GNF: Efficient Balanced Multi-View Graph Clustering via Good Neighbor Fusion. Integrating Neural-Symbolic Reasoning With Variational Causal Inference Network for Explanatory Visual Question Answering. Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing. Evaluation Metrics for Intelligent Generation of Graphical Game Assets: A Systematic Survey-Based Framework. Artificial Intelligence and Machine Learning Tools for Improving Early Warning Systems of Volcanic Eruptions: The Case of Stromboli.
×
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