语义分割主动学习中的部分注释

IF 9.6 1区 工程技术 Q1 CONSTRUCTION & BUILDING TECHNOLOGY Automation in Construction Pub Date : 2024-10-22 DOI:10.1016/j.autcon.2024.105828
B.G. Pantoja-Rosero , A. Chassignet , A. Rezaie , M. Kozinski , R. Achanta , K. Beyer
{"title":"语义分割主动学习中的部分注释","authors":"B.G. Pantoja-Rosero ,&nbsp;A. Chassignet ,&nbsp;A. Rezaie ,&nbsp;M. Kozinski ,&nbsp;R. Achanta ,&nbsp;K. Beyer","doi":"10.1016/j.autcon.2024.105828","DOIUrl":null,"url":null,"abstract":"<div><div>Semantic segmentation with deep learning plays a crucial role in various fields, including civil engineering, particularly in tasks such as damage assessment and urban planning. This paper addresses the challenge of efficiently training deep learning models for semantic segmentation with a limited set of annotated data, thus reducing the burden of ground truth labeling. An active learning strategy is introduced, leveraging partial annotations informed by predictions and uncertainties from previously trained models. Unlike other active learning frameworks, this approach not only facilitates the annotation of highly uncertain image regions but also targets those with low uncertainty, which often lead to false positives and negatives. The results demonstrate that using partial annotations within an active learning framework significantly reduces manual annotation efforts and training time without compromising model performance. These findings have substantial implications for the efficiency and scalability of deep learning in civil engineering, paving the way for future research in active learning and semantic segmentation.</div></div>","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":null,"pages":null},"PeriodicalIF":9.6000,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Partial annotations in active learning for semantic segmentation\",\"authors\":\"B.G. Pantoja-Rosero ,&nbsp;A. Chassignet ,&nbsp;A. Rezaie ,&nbsp;M. Kozinski ,&nbsp;R. Achanta ,&nbsp;K. Beyer\",\"doi\":\"10.1016/j.autcon.2024.105828\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Semantic segmentation with deep learning plays a crucial role in various fields, including civil engineering, particularly in tasks such as damage assessment and urban planning. This paper addresses the challenge of efficiently training deep learning models for semantic segmentation with a limited set of annotated data, thus reducing the burden of ground truth labeling. An active learning strategy is introduced, leveraging partial annotations informed by predictions and uncertainties from previously trained models. Unlike other active learning frameworks, this approach not only facilitates the annotation of highly uncertain image regions but also targets those with low uncertainty, which often lead to false positives and negatives. The results demonstrate that using partial annotations within an active learning framework significantly reduces manual annotation efforts and training time without compromising model performance. These findings have substantial implications for the efficiency and scalability of deep learning in civil engineering, paving the way for future research in active learning and semantic segmentation.</div></div>\",\"PeriodicalId\":8660,\"journal\":{\"name\":\"Automation in Construction\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":9.6000,\"publicationDate\":\"2024-10-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Automation in Construction\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0926580524005648\",\"RegionNum\":1,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CONSTRUCTION & BUILDING TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Automation in Construction","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0926580524005648","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

利用深度学习进行语义分割在包括土木工程在内的多个领域发挥着至关重要的作用,尤其是在损害评估和城市规划等任务中。本文探讨了如何利用有限的标注数据集高效地训练语义分割深度学习模型,从而减轻地面实况标注的负担。本文引入了一种主动学习策略,利用先前训练过的模型的预测和不确定性提供的部分注释。与其他主动学习框架不同的是,这种方法不仅有利于对高度不确定的图像区域进行标注,而且还能针对那些不确定性较低的区域进行标注,而不确定性较低的区域往往会导致假阳性和假阴性。研究结果表明,在主动学习框架内使用部分注释可显著减少人工注释工作量和训练时间,同时不会影响模型性能。这些发现对土木工程中深度学习的效率和可扩展性具有重大意义,为未来的主动学习和语义分割研究铺平了道路。
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
Partial annotations in active learning for semantic segmentation
Semantic segmentation with deep learning plays a crucial role in various fields, including civil engineering, particularly in tasks such as damage assessment and urban planning. This paper addresses the challenge of efficiently training deep learning models for semantic segmentation with a limited set of annotated data, thus reducing the burden of ground truth labeling. An active learning strategy is introduced, leveraging partial annotations informed by predictions and uncertainties from previously trained models. Unlike other active learning frameworks, this approach not only facilitates the annotation of highly uncertain image regions but also targets those with low uncertainty, which often lead to false positives and negatives. The results demonstrate that using partial annotations within an active learning framework significantly reduces manual annotation efforts and training time without compromising model performance. These findings have substantial implications for the efficiency and scalability of deep learning in civil engineering, paving the way for future research in active learning and semantic segmentation.
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
Automation in Construction
Automation in Construction 工程技术-工程:土木
CiteScore
19.20
自引率
16.50%
发文量
563
审稿时长
8.5 months
期刊介绍: Automation in Construction is an international journal that focuses on publishing original research papers related to the use of Information Technologies in various aspects of the construction industry. The journal covers topics such as design, engineering, construction technologies, and the maintenance and management of constructed facilities. The scope of Automation in Construction is extensive and covers all stages of the construction life cycle. This includes initial planning and design, construction of the facility, operation and maintenance, as well as the eventual dismantling and recycling of buildings and engineering structures.
期刊最新文献
Robust optimization model for traceable procurement of construction materials considering contract claims Editorial Board Rutting extraction from vehicle-borne laser point clouds Self-supervised monocular depth estimation on construction sites in low-light conditions and dynamic scenes Automated reinforcement of 3D-printed engineered cementitious composite beams
×
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