Generalizing to Unseen Domains: A Survey on Domain Generalization
The DOI matches its Crossref record; 287 of the 287 references it cites were found in a registry or an index.
Abstract
Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen distributions. Domain generalization (DG), i.e., out-of-distribution generalization, has attracted increasing interests in recent years. Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain. Great progress has been made in the area of domain generalization for years. This paper presents the first review of recent advances in this area. First, we provide a formal definition of domain generalization and discuss several related fields. We then thoroughly review the theories related to domain generalization and carefully analyze the theory behind generalization. We categorize recent algorithms into three classes: data manipulation, representation learning, and learning strategy, and present several popular algorithms in detail for each category. Third, we introduce the commonly used datasets, applications, and our open-sourced codebase for fair evaluation. Finally, we summarize existing literature and present some potential research topics for the future.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The use of transformer-based architectures can model the long-range dependencies in images and helps to mitigate problems such as the domain gap [21] problem.”
From A survey on deep learning-based monocular spacecraft pose estimation: Current state, limitations and prospects (2023) · cites this paper as [21]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“While synthetic data generation and laboratory data acquisition have been identified as the most tractable way to train and test such algorithms, the performance drops significantly on the test image domain compared to the train image domain, such problem being known as the domain gap [21].”
From A survey on deep learning-based monocular spacecraft pose estimation: Current state, limitations and prospects (2023) · cites this paper as [21]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Cortes, C., & Vapnik, V. (1995) · Machine-mediated learning · doi:10.1023/a:1022627411411 · Cited by 48,445
Pan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Generative adversarial networks
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020) · Communications of the ACM · doi:10.1145/3422622 · Cited by 18,384
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · cited 1×
“performance of a model by reducing overfitting [36], [169].”
Background
Research works printed but not linked: 14
- [53] P. Li, D. Li, W. Li, S. Gong, Y. Fu, and T. M. Hospedales, 'A simple feature augmentation for domain generalization,' in ICCV , 2021, pp. 8886-8895. - · DOI
- [203] B. Sch¨ olkopf, D. Janzing, J. Peters, E. Sgouritsa, K. Zhang, and J. M. Mooij, 'On causal and anticausal learning,' in ICML , 2012, pp. 1255-1262. -
- [217] T. Duboudin, E. Dellandr´ ea, C. Abgrall et al. , 'Encouraging intraclass diversity through a reverse contrastive loss for better singlesource domain generalization,' in ICCV , 2021. -
- [44] Y. Zhao, Z. Zhong, F. Yang, Z. Luo, Y. Lin et al. , 'Learning to generalize unseen domains via memory-based multi-source meta-learning for person re-identification,' in CVPR , 2021. - · DOI · Paper page
- [6] G. Blanchard, A. A. Deshmukh, ¨ U. Dogan, G. Lee, and C. Scott, 'Domain generalization by marginal transfer learning,' J. Mach. Learn. Res. , vol. 22, pp. 2-1, 2021. -
- [223] Z. Zhang, Y. Li, J. Wang, B. Liu, D. Li, X. Chen, Y. Guo, and Y. Liu, 'Remos: Reducing defect inheritance in transfer learning via relevant model slicing,' in 44th International Conference on Software Engineering (ICSE) , 2022. -
- [92] Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky, 'Domainadversarial training of neural networks,' J. Mach. Learn. Res. , vol. 17, pp. 59:1-59:35, 2016. -
- [262] R. Zhu and S. Li, 'Crossmatch: Cross-classifier consistency regularization for open-set single domain generalization,' in ICLR , 2021. -
- [225] Q. Yang, Y. Liu, Y. Cheng, Y. Kang, T. Chen, and H. Yu, 'Federated learning,' Synthesis Lectures on Artificial Intelligence and Machine Learning , vol. 13, no. 3, pp. 1-207, 2019. -
- [237] J. Taylor, B. Earnshaw, B. Mabey, M. Victors, and J. Yosinski, 'Rxrx1: An image set for cellular morphological variation across many experimental batches.' in ICLR , 2019. -
- [234] X. Peng, Q. Bai, X. Xia, Z. Huang, K. Saenko, and B. Wang, 'Moment matching for multi-source domain adaptation,' ICCV , pp. 1406-1415, 2019. - · DOI · Paper page
- [213] S. Sagawa, P. W. Koh, T. Hashimoto, and P. Liang, 'Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization,' in ICLR , 2020. -
- [154] Y. Wang, H. Li, L.-p. Chau, and A. C. Kot, 'Embracing the dark knowledge: Domain generalization using regularized knowledge distillation,' in Proceedings of the 29th ACM International Conference on Multimedia , 2021, pp. 2595-2604. -
- [15] T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey, 'Metalearning in neural networks: A survey,' IEEE TPAMI , 2020. -
Cited by
Items 1,001–1,003 of 1,003
Deep machine learning for biosignal analysis
Dissanayakage, P. T. T. (2024) · Queensland University of Technology · doi:10.5204/thesis.eprints.247177
He, X., Yang, B., & Lyu, F. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448305
Yu, M., Zhang, Y., Li, X., Zhang, R., Jiang, H., Gao, J., & Liu, Z. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446462
Metadata
- Authors
- Wang, J., Lan, C., Liu, C., Ouyang, Y., Qin, T., Lu, W., Chen, Y., Zeng, W., & Yu, P.
- Affiliations
- Microsoft Research Asia (China) (CN)
- Chinese University of Hong Kong, Shenzhen (CN)
- Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
- Chinese Academy of Sciences (CN)
- University of Illinois Chicago (US)
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 2022
- Pages
- 1-1
- ISSN
- 1041-4347 (ISSN-L)
- 1558-2191
- 2326-3865
- OpenAlex
- W3133542152
- Cited by
- 1,046
- References
- 282
- Citations by year
- 2026: 118 · 2025: 317 · 2024: 363 · 2023: 192 · 2022: 42
- FWCI
- 75.19
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Knowledge and Data Engineering (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- domain generalization, out-of-distribution generalization, generalization theory, data manipulation, representation learning, learning strategies, fair assessment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.