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

Xiaofeng Liu, Chaehwa Yoo, Fangxu Xing, Hyejin Oh, Georges El Fakhri, Je Won Kang, Jonghye Woo

Research output: Contribution to journalArticlepeer-review

60 Scopus citations

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.

Original languageEnglish
Article numbere25
JournalAPSIPA Transactions on Signal and Information Processing
Volume12
Issue number1
DOIs
StatePublished - 2022

Bibliographical note

Publisher Copyright:
© 2022 X. Liu, C. Yoo, F. Xing, H. Oh, G. El Fakhri, J. Kang and J. Woo.

Keywords

  • Deep learning
  • adversarial training
  • self training
  • transfer learning
  • unsupervised domain adaptation

Fingerprint

Dive into the research topics of 'Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives'. Together they form a unique fingerprint.

Cite this