APSIPA Transactions on Signal and Information Processing > Vol 11 > Issue 1

Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives

Xiaofeng Liu, Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, USA, xliu61@mgh.harvard.edu , Chaehwa Yoo, Department of Electronic and Electrical Engineering and Graduate Program in Smart Factory, Ewha Womans University, South Korea, Fangxu Xing, Massachusetts General Hospital and Harvard Medical School, USA, Hyejin Oh, Ewha Womans University, South Korea, Georges El Fakhri, Massachusetts General Hospital and Harvard Medical School, USA, Je-Won Kang, Ewha Womans University, South Korea, Jonghye Woo, Massachusetts General Hospital and Harvard Medical School, USA
 
Suggested Citation
Xiaofeng Liu, Chaehwa Yoo, Fangxu Xing, Hyejin Oh, Georges El Fakhri, Je-Won Kang and Jonghye Woo (2022), "Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives", APSIPA Transactions on Signal and Information Processing: Vol. 11: No. 1, e25. http://dx.doi.org/10.1561/116.00000192

Publication Date: 16 Aug 2022
© 2022 X. Liu, C. Yoo, F. Xing, H. Oh, G. El Fakhri, J. Kang and J. Woo
 
Subjects
 
Keywords
Deep learningunsupervised domain adaptationtransfer learningadversarial trainingself training
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 541 times

In this article:
Introduction 
Overview 
Methodology 
Applications 
Promising Directions 
Conclusion 
References 

Abstract

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success usually relies on two assumptions: (i) vast troves of labeled datasets are required for accurate model fitting, and (ii) training and testing data are independent and identically distributed. Its performance on unseen target domains, thus, is not guaranteed, especially when encountering out-of-distribution data at the adaptation stage. The performance drop on data in a target domain is a critical problem in deploying deep neural networks that are successfully trained on data in a source domain. Unsupervised domain adaptation (UDA) is proposed to counter this, by leveraging both labeled source domain data and unlabeled target domain data to carry out various tasks in the target domain. UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc. In this review, as a rapidly evolving topic, we provide a systematic comparison of its methods and applications. In addition, the connection of UDA with its closely related tasks, e.g., domain generalization and out-of-distribution detection, has also been discussed. Furthermore, deficiencies in current methods and possible promising directions are highlighted.

DOI:10.1561/116.00000192