• Open Access IconOpen Access
  • Cite Icon1100
  • https://doi.org/10.1109/tpami.2022.3195549Copy DOI Icon

Domain Generalization: A Survey.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
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.

Similar Papers
  • Dissertation
  • Citations1

Domain adaptation and generalization for visual recognition

  • Jan 01, 2017
  • Li Niu
  • Conference Article
  • Citations1

Multiple Domain-Adversarial Ensemble Learning for Domain Generalization

  • Jun 04, 2023
  • Ze-Yu Mi +2
  • Book Chapter
  • Citations9

Joint Autoencoders: A Flexible Meta-learning Framework

  • Jan 01, 2019
  • Baruch Epstein +2
  • Research Article
  • Citations172

Correlation-aware adversarial domain adaptation and generalization

  • Nov 28, 2019
  • Pattern Recognition
  • Mohammad Mahfujur Rahman +3
  • Research Article
  • Citations10

Iterative joint classifier and domain adaptation for visual transfer learning

  • Sep 29, 2021
  • International Journal of Machine Learning and Cybernetics
  • Shiva Noori Saray +1
  • Research Article
  • Citations3

Domain-Adaptive Framework for ACL Injury Diagnosis Utilizing Contrastive Learning Techniques

  • Aug 14, 2024
  • Electronics
  • Weiqiang Liu +3
  • PDF
  • Research Article
  • Citations10

Using Domain Adaptation and Inductive Transfer Learning to Improve Patient Outcome Prediction in the Intensive Care Unit: Retrospective Observational Study.

  • Aug 21, 2024
  • Journal of medical Internet research
  • Maruthi Kumar Mutnuri +3
  • Research Article
  • Citations21

Adversarial transfer learning for cross-domain visual recognition

  • Jul 15, 2020
  • Knowledge-Based Systems
  • Shanshan Wang +2
  • Book Chapter
  • Citations3

Learning Cross-Domain Features for Domain Generalization on Point Clouds

  • Jan 01, 2022
  • Hang Xiao +2
  • Research Article
  • Citations151

Adaptive Intermediate Class-Wise Distribution Alignment: A Universal Domain Adaptation and Generalization Method for Machine Fault Diagnosis.

  • Mar 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Quan Qian +2
  • PDF
  • Research Article
  • Citations32

A Kernelized Unified Framework for Domain Adaptation

  • Jan 01, 2019
  • IEEE Access
  • Rakesh Kumar Sanodiya +3
  • Research Article
  • Citations27

Domain adaptation and transfer learning for failure detection and failure-cause identification in optical networks across different lightpaths [Invited

  • Dec 01, 2021
  • Journal of Optical Communications and Networking
  • Francesco Musumeci +7
  • Research Article

Deep Learning Approaches for Speech Recognition and Synthesis

  • Apr 15, 2025
  • International Journal on Advanced Computer Engineering and Communication Technology
  • Anasica +1
  • Research Article
  • Citations5

Representation Learning with Multiple Lipschitz-Constrained Alignments on Partially-Labeled Cross-Domain Data

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Songlei Jian +3
  • Research Article
  • Citations56

A Review of Recent Work in Transfer Learning and Domain Adaptation for Natural Language Processing of Electronic Health Records

  • Aug 01, 2021
  • Yearbook of Medical Informatics
  • Egoitz Laparra +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.