首页|期刊导航|International Journal of Agricultural and Biological Engineering|Contrastive learning with multi-centroid proxy loss for domain adaptive cattle identification

Contrastive learning with multi-centroid proxy loss for domain adaptive cattle identificationOA

中文摘要

Visual identification of cattle in the wild is essential to provide continuous individual monitoring applicable to precision livestock farming.Supervised learning heavily relies on annotation,which is really a time-consuming work for cattle labeling.Domain adaptive cattle identification aims at transferring knowledge learned from the source domain with rich annotations to the unlabeled target domain.Pseudo-label-based contrastive learning with a unique centroid inevitably incorporates information from different identities due to imperfect clustering.Thus,a contrastive learning with multi-centroid proxy(CL-MCP)for domain adaptive cattle identification was proposed with more local centroids to enhance the reliability of pseudo-labels for a more compact cluster in the target feature space.Firstly,a target domain feature storage module and a momentum update strategy were proposed to progressively update the target domain features for effective training with a stable clustering space.Secondly,a multi-centroid storage module and a proxy representation method were proposed to learn more informative local clusters and provide a representative proxy for each class to efficiently form correct clusters in the feature space.Finally,the domain-specific proxy-level contrastive loss was presented to enlarge the similarity between a query and its positive proxy while reducing the similarities among the query and its negative proxies for more compact clustering.It is encouraging to find that our CL-MCP mechanism performs better than Deep Metric Learning(DML)approaches for identifying individuals from different farms or unseen viewpoints or of a new breed.The datasets,MVCAID100,CNSID100,and Cattle-2022,are available on https://pan.baidu.com/s/19hoWd__7NMLvdLNp-otDSRg(code:d3oa).The results of this study can provide an effective cattle identification method applicable to automated production monitoring,behavioral and physiological observation,health and welfare supervision in precision livestock farming,and animal science research.

Jianmin Zhao;Qiusheng Lian;Yufei Zhao

School of Automation and Electrical Engineering,Inner Mongolia University of Science and Technology,Baotou 014010,Inner Mongolia,ChinaSchool of Information Science and Technology,Yanshan University,Qinhuangdao 066004,Hebei,ChinaVocational and Technical College,Inner Mongolia Agricultural University,Baotou 014109,Inner Mongolia,China

农业科技

cattle identificationprecision livestock farmingunsupervised domain adaptation(UDA)contrastive learningunsupervised learning

《International Journal of Agricultural and Biological Engineering》 2026 (1)

P.187-196,10

supported in part by the National Natural Science Foundation of China(Grant No.32460858)the Natural Science Foundation of Inner Mongolia Autonomous Region in China(Grant No.2023MS06014 and Grant No.2019LH06006)Inner Mongolia Autonomous Region Science and Technology Plan Project in China(Grant No.2021GG0224)Fundamental Research Funds for Inner Mongolia University of Science&Technology[088]Inner Mongolia Autonomous Region Science and Technology Special Project in China(Grant No.2019ZD025).

10.25165/j.ijabe.20261901.9242

评论