Cumulative unsupervised multi-domain adaptation for Holstein cattle re-identification

IF 8.2 Q1 AGRICULTURE, MULTIDISCIPLINARY
Fabian Dubourvieux , Guillaume Lapouge , Angélique Loesch , Bertrand Luvison , Romaric Audigier
{"title":"Cumulative unsupervised multi-domain adaptation for Holstein cattle re-identification","authors":"Fabian Dubourvieux ,&nbsp;Guillaume Lapouge ,&nbsp;Angélique Loesch ,&nbsp;Bertrand Luvison ,&nbsp;Romaric Audigier","doi":"10.1016/j.aiia.2023.10.002","DOIUrl":null,"url":null,"abstract":"<div><p>In dairy farming, ensuring the health of each cow and minimizing economic losses requires individual monitoring, achieved through cow <em>Re</em>-Identification (Re-ID). Computer vision-based Re-ID relies on visually distinguishing features, such as the distinctive coat patterns of breeds like Holstein.</p><p>However, annotating every cow in each farm is cost-prohibitive. Our objective is to develop <em>Re</em>-ID methods applicable to both labeled and unlabeled farms, accommodating new individuals and diverse environments. Unsupervised Domain Adaptation (UDA) techniques bridge this gap, transferring knowledge from labeled source domains to unlabeled target domains, but have only been mainly designed for pedestrian and vehicle <em>Re</em>-ID applications.</p><p>Our work introduces Cumulative Unsupervised Multi-Domain Adaptation (CUMDA) to address challenges of limited identity diversity and diverse farm appearances. CUMDA accumulates knowledge from all domains, enhancing specialization in known domains and improving generalization to unseen domains. Our contributions include a CUMDA method adapting to multiple unlabeled target domains while preserving source domain performance, along with extensive cross-dataset experiments on three cattle <em>Re</em>-ID datasets. These experiments demonstrate significant enhancements in source preservation, target domain specialization, and generalization to unseen domains.</p></div>","PeriodicalId":52814,"journal":{"name":"Artificial Intelligence in Agriculture","volume":null,"pages":null},"PeriodicalIF":8.2000,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2589721723000429/pdfft?md5=415adc99dee89219367d287b9bd79295&pid=1-s2.0-S2589721723000429-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence in Agriculture","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2589721723000429","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

In dairy farming, ensuring the health of each cow and minimizing economic losses requires individual monitoring, achieved through cow Re-Identification (Re-ID). Computer vision-based Re-ID relies on visually distinguishing features, such as the distinctive coat patterns of breeds like Holstein.

However, annotating every cow in each farm is cost-prohibitive. Our objective is to develop Re-ID methods applicable to both labeled and unlabeled farms, accommodating new individuals and diverse environments. Unsupervised Domain Adaptation (UDA) techniques bridge this gap, transferring knowledge from labeled source domains to unlabeled target domains, but have only been mainly designed for pedestrian and vehicle Re-ID applications.

Our work introduces Cumulative Unsupervised Multi-Domain Adaptation (CUMDA) to address challenges of limited identity diversity and diverse farm appearances. CUMDA accumulates knowledge from all domains, enhancing specialization in known domains and improving generalization to unseen domains. Our contributions include a CUMDA method adapting to multiple unlabeled target domains while preserving source domain performance, along with extensive cross-dataset experiments on three cattle Re-ID datasets. These experiments demonstrate significant enhancements in source preservation, target domain specialization, and generalization to unseen domains.

荷斯坦牛再识别的累积无监督多域自适应
在奶牛养殖中,为了确保每头奶牛的健康并最大限度地减少经济损失,需要通过奶牛重新识别(Re-ID)进行个体监测。基于计算机视觉的Re-ID依赖于视觉上的区分特征,比如像霍尔斯坦犬这样的品种独特的皮毛图案。然而,对每个农场的每头奶牛进行注释成本过高。我们的目标是开发适用于标记和未标记农场的Re-ID方法,以适应新的个体和不同的环境。无监督域自适应(UDA)技术弥补了这一差距,将知识从标记的源域转移到未标记的目标域,但主要用于行人和车辆的Re-ID应用。我们的工作引入了累积无监督多域适应(CUMDA)来解决有限的身份多样性和多样化农场外观的挑战。CUMDA从所有领域积累知识,增强了已知领域的专门化,提高了对未知领域的泛化。我们的贡献包括一种适应多个未标记目标域同时保持源域性能的CUMDA方法,以及在三个牛Re-ID数据集上进行的广泛的跨数据集实验。这些实验证明了在源保存、目标领域专门化和对未知领域的泛化方面的显著增强。
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 求助全文
来源期刊
Artificial Intelligence in Agriculture
Artificial Intelligence in Agriculture Engineering-Engineering (miscellaneous)
CiteScore
21.60
自引率
0.00%
发文量
18
审稿时长
12 weeks
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信