{"title":"HSSDA: Hierarchical relation aided Semi-Supervised Domain Adaptation","authors":"Xiechao Guo , Ruiping Liu , Dandan Song","doi":"10.1016/j.aiopen.2022.11.001","DOIUrl":null,"url":null,"abstract":"<div><p>The mainstream domain adaptation (DA) methods transfer the supervised source domain knowledge to the unsupervised or semi-supervised target domain, so as to assist the classification task in the target domain. Usually the supervision only contains the class label of the object. However, when human beings recognize a new object, they will not only learn the class label of the object, but also correlate the object to its parent class, and use this information to learn the similarities and differences between child classes. Our model utilizes hierarchical relations via making the parent class label of labeled data (all the source domain data and part of target domain data) as a part of supervision to guide prototype learning module vbfd to learn the parent class information encoding, so that the prototypes of the same parent class are closer in the prototype space, which leads to better classification results. Inspired by this mechanism, we propose a <strong>Hierarchical relation aided Semi-Supervised Domain Adaptation (HSSDA)</strong> method which incorporates the hierarchical relations into the Semi-Supervised Domain Adaptation (SSDA) method to improve the classification results of the model. Our model performs well on the DomainNet dataset, and gets the state-of-the-art results in the semi-supervised DA problem.</p></div>","PeriodicalId":100068,"journal":{"name":"AI Open","volume":"3 ","pages":"Pages 156-161"},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266665102200016X/pdfft?md5=acdf10fbc8ecc16b703bc63cf409d5c7&pid=1-s2.0-S266665102200016X-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"AI Open","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S266665102200016X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The mainstream domain adaptation (DA) methods transfer the supervised source domain knowledge to the unsupervised or semi-supervised target domain, so as to assist the classification task in the target domain. Usually the supervision only contains the class label of the object. However, when human beings recognize a new object, they will not only learn the class label of the object, but also correlate the object to its parent class, and use this information to learn the similarities and differences between child classes. Our model utilizes hierarchical relations via making the parent class label of labeled data (all the source domain data and part of target domain data) as a part of supervision to guide prototype learning module vbfd to learn the parent class information encoding, so that the prototypes of the same parent class are closer in the prototype space, which leads to better classification results. Inspired by this mechanism, we propose a Hierarchical relation aided Semi-Supervised Domain Adaptation (HSSDA) method which incorporates the hierarchical relations into the Semi-Supervised Domain Adaptation (SSDA) method to improve the classification results of the model. Our model performs well on the DomainNet dataset, and gets the state-of-the-art results in the semi-supervised DA problem.