Unsupervised Domain Adaptation [E-Book] : Recent Advances and Future Perspectives / by Jingjing Li, Lei Zhu, Zhekai Du.
Unsupervised 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 applicab...
Saved in:
Full text |
|
Personal Name(s): | Li, Jingjing, author |
Du, Zhekai, author / Zhu, Lei, author | |
Edition: |
1st edition 2024. |
Imprint: |
Singapore :
Springer,
2024
|
Physical Description: |
XVI, 223 pages 78 illustrations, 44 illustrations in color (online resource) |
Note: |
englisch |
ISBN: |
9789819710256 |
DOI: |
10.1007/978-981-97-1025-6 |
Series Title: |
/* Depending on the record driver, $field may either be an array with
"name" and "number" keys or a flat string containing only the series
name. We should account for both cases to maximize compatibility. */?>
Machine Learning: Foundations, Methodologies, and Applications
|
Subject (LOC): |
- Chapter 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.