LEADER 04368nam 22006375 450 001 9910851990403321 005 20250807145452.0 010 $a981-9710-25-1 024 7 $a10.1007/978-981-97-1025-6 035 $a(CKB)31636466800041 035 $a(DE-He213)978-981-97-1025-6 035 $a(MiAaPQ)EBC31302732 035 $a(Au-PeEL)EBL31302732 035 $a(EXLCZ)9931636466800041 100 $a20240422d2024 u| 0 101 0 $aeng 135 $aur||||||||||| 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aUnsupervised Domain Adaptation $eRecent Advances and Future Perspectives /$fby Jingjing Li, Lei Zhu, Zhekai Du 205 $a1st ed. 2024. 210 1$aSingapore :$cSpringer Nature Singapore :$cImprint: Springer,$d2024. 215 $a1 online resource (XVI, 223 p. 78 illus., 44 illus. in color.) 225 1 $aMachine Learning: Foundations, Methodologies, and Applications,$x2730-9916 311 08$a981-9710-24-3 327 $aChapter 1. Introduction to Domain Adaptation -- Chapter 2. Unsupervised Domain Adaptation Techniques -- Chapter 3. Criterion Optimization-Based Unsupervised Domain -- Chapter 4. Bi-Classifier Adversarial Learning-Based Unsupervised Domain -- Chapter 5. Source-Free Unsupervised Domain Adaptation -- Chapter 6. Active Learning for Unsupervised Domain Adaptation -- Chapter 7. Continual Test-Time Unsupervised Domain Adaptation -- Chapter 8. Applications -- Chapter 9. Research Frontier. 330 $aUnsupervised domain adaptation (UDA) is a challenging problem in machine learning where the model is trained on a source domain with labeled data and tested on a target domain with unlabeled data. In recent years, UDA has received significant attention from the research community due to its applicability in various real-world scenarios. This book provides a comprehensive review of state-of-the-art UDA methods and explores new variants of UDA that have the potential to advance the field. The book begins with a clear introduction to the UDA problem and is mainly organized into four technical sections, each focused on a specific piece of UDA research. The first section covers criterion optimization-based UDA, which aims to learn domain-invariant representations by minimizing the discrepancy between source and target domains. The second section discusses bi-classifier adversarial learning-based UDA, which creatively leverages adversarial learning by conducting a minimax game between the feature extractor and two task classifiers. The third section introduces source-free UDA, a novel UDA setting that does not require any raw data from the source domain. The fourth section presents active learning for UDA, which combines domain adaptation and active learning to reduce the amount of labeled data needed for adaptation. This book is suitable for researchers, graduate students, and practitioners who are interested in UDA and its applications in various fields, primarily in computer vision. The chapters are authored by leading experts in the field and provide a comprehensive and in-depth analysis of the current UDA methods and new directions for future research. With its broad coverage and cutting-edge research, this book is a valuable resource for anyone looking to advance their knowledge of UDA. 410 0$aMachine Learning: Foundations, Methodologies, and Applications,$x2730-9916 606 $aMachine learning 606 $aArtificial intelligence$xData processing 606 $aData mining 606 $aDistribution (Probability theory) 606 $aMachine Learning 606 $aData Science 606 $aData Mining and Knowledge Discovery 606 $aDistribution Theory 615 0$aMachine learning. 615 0$aArtificial intelligence$xData processing. 615 0$aData mining. 615 0$aDistribution (Probability theory) 615 14$aMachine Learning. 615 24$aData Science. 615 24$aData Mining and Knowledge Discovery. 615 24$aDistribution Theory. 676 $a006.31 700 $aLi$b Jingjing$01772177 702 $aZhu$b Lei 702 $aDu$b Zhekai 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910851990403321 996 $aUnsupervised Domain Adaptation$94272243 997 $aUNINA