Domain Generalization: A Survey

Kaiyang Zhou*, Ziwei Liu, Yu Qiao, Tao Xiang, Chen Change Loy

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

107 Citations (Scopus)

Abstract

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely on the i.i.d. assumption on source/target data, which is often violated in practice due to domain shift. Domain generalization (DG) aims to achieve OOD generalization by using only source data for model learning. Over the last ten years, research in DG has made great progress, leading to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, to name a few; DG has also been studied in various application areas including computer vision, speech recognition, natural language processing, medical imaging, and reinforcement learning. In this paper, for the first time a comprehensive literature review in DG is provided to summarize the developments over the past decade. Specifically, we first cover the background by formally defining DG and relating it to other relevant fields like domain adaptation and transfer learning. Then, we conduct a thorough review into existing methods and theories. Finally, we conclude this survey with insights and discussions on future research directions.

Original languageEnglish
Pages (from-to)4396-4415
Number of pages20
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume45
Issue number4
Early online date1 Aug 2022
DOIs
Publication statusPublished - Apr 2023

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

User-Defined Keywords

  • Out-of-distribution generalization
  • domain shift
  • model robustness
  • machine learning

Fingerprint

Dive into the research topics of 'Domain Generalization: A Survey'. Together they form a unique fingerprint.

Cite this