{"title":"用于无监督领域适应的动态参数化学习","authors":"Runhua Jiang, Yahong Han","doi":"10.1631/fitee.2200631","DOIUrl":null,"url":null,"abstract":"<p>Unsupervised domain adaptation enables neural networks to transfer from a labeled source domain to an unlabeled target domain by learning domain-invariant representations. Recent approaches achieve this by directly matching the marginal distributions of these two domains. Most of them, however, ignore exploration of the dynamic trade-off between domain alignment and semantic discrimination learning, thus rendering them susceptible to the problems of negative transfer and outlier samples. To address these issues, we introduce the dynamic parameterized learning framework. First, by exploring domain-level semantic knowledge, the dynamic alignment parameter is proposed, to adaptively adjust the optimization steps of domain alignment and semantic discrimination learning. Besides, for obtaining semantic-discriminative and domain-invariant representations, we propose to align training trajectories on both source and target domains. Comprehensive experiments are conducted to validate the effectiveness of the proposed methods, and extensive comparisons are conducted on seven datasets of three visual tasks to demonstrate their practicability.</p>","PeriodicalId":12608,"journal":{"name":"Frontiers of Information Technology & Electronic Engineering","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Dynamic parameterized learning for unsupervised domain adaptation\",\"authors\":\"Runhua Jiang, Yahong Han\",\"doi\":\"10.1631/fitee.2200631\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Unsupervised domain adaptation enables neural networks to transfer from a labeled source domain to an unlabeled target domain by learning domain-invariant representations. Recent approaches achieve this by directly matching the marginal distributions of these two domains. Most of them, however, ignore exploration of the dynamic trade-off between domain alignment and semantic discrimination learning, thus rendering them susceptible to the problems of negative transfer and outlier samples. To address these issues, we introduce the dynamic parameterized learning framework. First, by exploring domain-level semantic knowledge, the dynamic alignment parameter is proposed, to adaptively adjust the optimization steps of domain alignment and semantic discrimination learning. Besides, for obtaining semantic-discriminative and domain-invariant representations, we propose to align training trajectories on both source and target domains. Comprehensive experiments are conducted to validate the effectiveness of the proposed methods, and extensive comparisons are conducted on seven datasets of three visual tasks to demonstrate their practicability.</p>\",\"PeriodicalId\":12608,\"journal\":{\"name\":\"Frontiers of Information Technology & Electronic Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2023-12-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers of Information Technology & Electronic Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1631/fitee.2200631\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers of Information Technology & Electronic Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1631/fitee.2200631","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
Dynamic parameterized learning for unsupervised domain adaptation
Unsupervised domain adaptation enables neural networks to transfer from a labeled source domain to an unlabeled target domain by learning domain-invariant representations. Recent approaches achieve this by directly matching the marginal distributions of these two domains. Most of them, however, ignore exploration of the dynamic trade-off between domain alignment and semantic discrimination learning, thus rendering them susceptible to the problems of negative transfer and outlier samples. To address these issues, we introduce the dynamic parameterized learning framework. First, by exploring domain-level semantic knowledge, the dynamic alignment parameter is proposed, to adaptively adjust the optimization steps of domain alignment and semantic discrimination learning. Besides, for obtaining semantic-discriminative and domain-invariant representations, we propose to align training trajectories on both source and target domains. Comprehensive experiments are conducted to validate the effectiveness of the proposed methods, and extensive comparisons are conducted on seven datasets of three visual tasks to demonstrate their practicability.
期刊介绍:
Frontiers of Information Technology & Electronic Engineering (ISSN 2095-9184, monthly), formerly known as Journal of Zhejiang University SCIENCE C (Computers & Electronics) (2010-2014), is an international peer-reviewed journal launched by Chinese Academy of Engineering (CAE) and Zhejiang University, co-published by Springer & Zhejiang University Press. FITEE is aimed to publish the latest implementation of applications, principles, and algorithms in the broad area of Electrical and Electronic Engineering, including but not limited to Computer Science, Information Sciences, Control, Automation, Telecommunications. There are different types of articles for your choice, including research articles, review articles, science letters, perspective, new technical notes and methods, etc.