Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
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.
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.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Multi-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738 · cited 1×
“Instead, adversarial training at both feature and image levels have been widely used (Yu and Koltun, 2015; Tsai et al., 2018; Mei et al., 2020a).”
Deep CORAL: Correlation Alignment for Deep Domain Adaptation
Sun, B., & Saenko, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-49409-8_35 · Cited by 3,757 · cited 4×
“Zellinger et al. (2017) compare their CMD methods with other discrepancy-based methods, e.g., DDC (Tzeng et al., 2014), deep CROAL (Sun and Saenko, 2016), DLID (Chopra et al., 2013), AdaBN (Li et al., 2016)) and adversarial DANN (Ganin and Lempitsky, 2015).”
BackgroundMethodInfluentialWu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601 · cited 1×
“In modern deep neural networks, batch normalization (BN) layers have played an important role in achieving faster training (Ioffe and Szegedy, 2015), smoother optimization, and more stable convergence (Wu and He, 2018), due to its insensitivity to initialization (Santurkar et al., 2018).”
BackgroundWhat Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Kendall, A., & Gal, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.04977 · Cited by 3,088 · cited 1×
“In learning-based tasks, two kinds of uncertainty exist, including an aleatoric uncertainty and an epistemic uncertainty (Der Kiureghian and Ditlevsen, 2009; Kendall and Gal, 2017; Hu et al., 2019).”
BackgroundOn the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
A survey on semi-supervised learning
van Engelen, J. E., & Hoos, H. H. (2020) · Machine Learning · doi:10.1007/s10994-019-05855-6 · Cited by 2,666 · cited 1×
“In such circumstances, labeling a small set of target domain data could be a viable solution (Van Engelen and Hoos, 2020).”
BackgroundAleatory or epistemic? Does it matter?
Kiureghian, A. D., & Ditlevsen, O. (2009) · Structural Safety · doi:10.1016/j.strusafe.2008.06.020 · Cited by 2,454 · cited 2×
“In learning-based tasks, two kinds of uncertainty exist, including an aleatoric uncertainty and an epistemic uncertainty (Der Kiureghian and Ditlevsen, 2009; Kendall and Gal, 2017; Hu et al., 2019).”
Background
Cited by
Aldoseri, A., Al-Khalifa, K. N., & Hamouda, A. M. (2023) · Applied Sciences · doi:10.3390/app13127082 · Cited by 716
Deep Learning in NLP for Anomalous HTTP Requests Detection
Anh Nguyen, M. T., Tong, V., Souihi, S. B., & Souihi, S. (2023) · 2023 19th International Conference on Network and Service Management (CNSM) · doi:10.23919/cnsm59352.2023.10327888 · Cited by 12
“According to [18], Domain Adaptation (DA) approaches can be categorized into two different categories, namely, (i) Domain Invariant feature learning approach and (ii) Adversarial-based Domain Adaptation approach.”
BackgroundGuo, S., Wang, Y., Liu, Y., Zhang, X., & Tang, B. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107756 · Cited by 7
Metadata
- Authors
- Liu, X., Yoo, C., Xing, F., Oh, H., El Fakhri, G., Kang, J.-W., & Woo*, J.
- Venue
- APSIPA Transactions on Signal and Information Processing
- Publisher
- Emerald
- Published
- 2022-08-16
- Volume
- 11
- Issue
- 1
- Pages
- 1-51
- ISSN
- 2048-7703 (ISSN-L)
- OpenAlex
- W4292198371
- Cited by
- 299
- References
- 29
- FWCI
- 20.20
- Type
- journal article
- Language
- en
- Open access
- gold
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.