混合域自适应改进现实世界监控中的语义分割

S'ebastien Pi'erard, A. Cioppa, Anaïs Halin, Renaud Vandeghen, Maxime Zanella, B. Macq, S. Mahmoudi, Marc Van Droogenbroeck
{"title":"混合域自适应改进现实世界监控中的语义分割","authors":"S'ebastien Pi'erard, A. Cioppa, Anaïs Halin, Renaud Vandeghen, Maxime Zanella, B. Macq, S. Mahmoudi, Marc Van Droogenbroeck","doi":"10.1109/WACVW58289.2023.00007","DOIUrl":null,"url":null,"abstract":"Various tasks encountered in real-world surveillance can be addressed by determining posteriors (e.g. by Bayesian inference or machine learning), based on which critical decisions must be taken. However, the surveillance domain (acquisition device, operating conditions, etc.) is often unknown, which prevents any possibility of scene-specific optimization. In this paper, we define a probabilistic framework and present a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors. Our proposed algorithm is applicable when the probability measure associated with the target domain is a convex combination of the probability measures of the source domains. It makes use of source models and a domain discriminator model trained off-line to compute posteriors adapted on the fly to the target domain. Finally, we show the effectiveness of our algorithm for the task of semantic segmentation in real-world surveillance. The code is publicly available at https://github.com/rvandeghen/MDA.","PeriodicalId":306545,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance\",\"authors\":\"S'ebastien Pi'erard, A. Cioppa, Anaïs Halin, Renaud Vandeghen, Maxime Zanella, B. Macq, S. Mahmoudi, Marc Van Droogenbroeck\",\"doi\":\"10.1109/WACVW58289.2023.00007\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Various tasks encountered in real-world surveillance can be addressed by determining posteriors (e.g. by Bayesian inference or machine learning), based on which critical decisions must be taken. However, the surveillance domain (acquisition device, operating conditions, etc.) is often unknown, which prevents any possibility of scene-specific optimization. In this paper, we define a probabilistic framework and present a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors. Our proposed algorithm is applicable when the probability measure associated with the target domain is a convex combination of the probability measures of the source domains. It makes use of source models and a domain discriminator model trained off-line to compute posteriors adapted on the fly to the target domain. Finally, we show the effectiveness of our algorithm for the task of semantic segmentation in real-world surveillance. The code is publicly available at https://github.com/rvandeghen/MDA.\",\"PeriodicalId\":306545,\"journal\":{\"name\":\"2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)\",\"volume\":\"136 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WACVW58289.2023.00007\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WACVW58289.2023.00007","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

现实世界监控中遇到的各种任务可以通过确定后验来解决(例如通过贝叶斯推理或机器学习),必须在此基础上做出关键决策。然而,监控领域(采集设备,操作条件等)通常是未知的,这阻碍了任何场景特定优化的可能性。在本文中,我们定义了一个概率框架,并给出了一种后验的无监督多到无穷域自适应算法的形式化证明。当与目标域相关的概率测度是源域概率测度的凸组合时,本文提出的算法是适用的。它利用源模型和离线训练的域鉴别器模型来计算动态适应目标域的后验。最后,我们展示了我们的算法在现实世界监控中语义分割任务的有效性。该代码可在https://github.com/rvandeghen/MDA上公开获得。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Mixture Domain Adaptation to Improve Semantic Segmentation in Real-World Surveillance
Various tasks encountered in real-world surveillance can be addressed by determining posteriors (e.g. by Bayesian inference or machine learning), based on which critical decisions must be taken. However, the surveillance domain (acquisition device, operating conditions, etc.) is often unknown, which prevents any possibility of scene-specific optimization. In this paper, we define a probabilistic framework and present a formal proof of an algorithm for the unsupervised many-to-infinity domain adaptation of posteriors. Our proposed algorithm is applicable when the probability measure associated with the target domain is a convex combination of the probability measures of the source domains. It makes use of source models and a domain discriminator model trained off-line to compute posteriors adapted on the fly to the target domain. Finally, we show the effectiveness of our algorithm for the task of semantic segmentation in real-world surveillance. The code is publicly available at https://github.com/rvandeghen/MDA.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Subjective and Objective Video Quality Assessment of High Dynamic Range Sports Content Improving the Detection of Small Oriented Objects in Aerial Images Image Quality Assessment using Semi-Supervised Representation Learning A Principal Component Analysis-Based Approach for Single Morphing Attack Detection Can Machines Learn to Map Creative Videos to Marketing Campaigns?
×
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