文献类型：期刊文献

英文题名：Relationship constraint deep metric learning

作者：Zhang, Yanbing[1,2];Xiao, Ting[1,2];Wang, Zhe[1,2];Wang, Xinru[1,2];Feng, Wenyi[1,2];Fu, Zhiling[1,2];Yang, Hai[1,2]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Smart Mfg Energy Chem Proc, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China

年份：2024

卷号：54

期号：8

起止页码：6654

外文期刊名：APPLIED INTELLIGENCE

收录：;EI(收录号：20242116136118);WOS:【SCI-EXPANDED(收录号:WOS:001228729000003)】；

基金：This work is supported by National Key Research and Development Program of China under Grant 2022YFB3203500, Natural Science Foundation of China under Grant No. 62076094, Shanghai Science and Technology Program "Federated based cross-domain and cross-task incremental learning" under Grant No. 21511100800, Chinese Defense Program of Science and Technology under Grant No. 2021-JCJQ-JJ-0041, China Aerospace Science and Technology Corporation Industry-University-Research Cooperation Foundation of the Eighth Research Institute under Grant No. SAST2021-007.

语种：英文

外文关键词：Deep metric learning; Data relationship; Proxy relationship constraint; Sample relationship constraint; Proxy correction

摘要：Deep metric learning (DML) models aim to learn semantically meaningful representations in which similar samples are pulled together and dissimilar samples are pushed apart. However, the classification effect is limited due to the high time complexity of previous models and their poor performance in extracting data relationships. This paper presents a novel relationship constraint deep metric learning (RCDML) approach, including proxy relationship constraint (PRC) and sample relationship constraint (SRC) for inter-class separability and intra-class compactness, to solve the above problems and improve the classification effect. The PRC combines the proxy-to-proxy relationship loss term with the proxy-to-sample relationship loss function tomaximize the proxy features, hence enhancing inter-class separability by decreasing proxy similarity. Additionally, the SRCcombines the sample-to-sample relationship loss termwith the proxy-to-sample relationship loss function tomaximize the sample features, which promotes intra-class compactness by increasing the similarity between the most different samples of the same class. Unlike existing proxy-based and pair-based methods, the relationship constraint framework uses a diverse range of proxy and sample data relationships. In addition, the proxy correction (PC) module is used to optimize the proxy. Extensive tests conducted on the widely popular CUB-200-2011, CARS-196, and SOP datasets show that the framework is effective and attains state-of-the-art performance.