Unsupervised Domain Adaptation of Object Detectors: A Survey
Open accessThe DOI matches its Crossref record; 213 of the 213 references it cites were found in a registry or an index.
Abstract
Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on the availability of large-scale annotated datasets. Due to this, model performance drops drastically when evaluated on label-scarce datasets having visually distinct images, termed as domain adaptation problem. There are a plethora of works to adapt classification and segmentation models to label-scarce target dataset through unsupervised domain adaptation. Considering that detection is a fundamental task in computer vision, many recent works have focused on developing novel domain adaptive detection techniques. Here, we describe in detail the domain adaptation problem for detection and present an extensive survey of the various methods. Furthermore, we highlight strategies proposed and the associated shortcomings. Subsequently, we identify multiple aspects of the problem that are most promising for future research. We believe that this survey shall be valuable to the pattern recognition experts working in the fields of computer vision, biometrics, medical imaging, and autonomous navigation by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Items 201–213 of 213
SPLAT: Semantic Pixel-Level Adaptation Transforms for DetectionPreprint
Tzeng, E., Burns, K., Saenko, K., & Darrell, T. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.00929 · Cited by 15
DALocNet: Improving Localization Accuracy for Domain Adaptive Object Detection
Yu, Y., Xu, X., Hu, X., & Heng, P. (2019) · IEEE Access · doi:10.1109/access.2019.2915607 · Cited by 15
Thermal Object Detection using Domain Adaptation through Style Consistency.Preprint
Munir, F., Azam, S., Rafique, M. A., Sheri, A. M., & Jeon, M. (2020) · arXiv (Cornell University) · Cited by 13
Domain-Invariant Region Proposal Network For Cross-Domain Detection
Yang, X., Wan, S., & Jin, P. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102766 · Cited by 12 · cited 1×
“There are several subsequent works such as [56], [64], [67], [71], [77], [115], [119], [122], [125], [127] that utilize the adversarial feature learning strategies discussed in this section.”
BackgroundAssociative Partial Domain AdaptationPreprint
Kim, Y., Hong, S., Yang, S., Kang, S., Jeon, Y., & Kim, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.03111 · Cited by 10
Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection
Scheck, T., Grassi, A., & Hirtz, G. (2021) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0010202503190327 · Cited by 9
Deeply Aligned Adaptation for Cross-domain Object DetectionPreprint
Fu, M., Xie, Z., Li, W., & Duan, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.02093 · Cited by 6 · cited 1×
“Furthermore,therearemanyotherinterestingworksavailableas pre-print[76],[81],[135],[136],[137],[138],[139].”
Sun, T., Chen, J., & Ng, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.13970 · Cited by 6
Domain Adaptive Object Detection via Feature Separation and AlignmentPreprint
Liang, C., Zhao, Z., Liu, J., & Zhang, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.08689 · Cited by 5
Region Proposal Oriented Approach for Domain Adaptive Object Detection
Alqasir, H., Muselet, D., & Ducottet, C. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-40605-9_4 · Cited by 4
Channel-wise Alignment for Adaptive Object DetectionPreprint
Yang, H., Jiang, S., Zhu, X., Huang, M.-Y., Shen, Z., Liu, C., & Shi, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.02862 · Cited by 4 · cited 3×
“Furthermore,therearemanyotherinterestingworksavailableas pre-print[76],[81],[135],[136],[137],[138],[139].”
BackgroundLearning a Domain Classifier Bank for Unsupervised Adaptive Object DetectionPreprint
Tang, S., Cheng, Z., Pu, S., Guo, D., Niu, Y. F., & Wu, F. Q. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.02595 · Cited by 3
Chen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Research works printed but not linked: 2
- Chen, 2021, Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 12571
- 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
Cited by
Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives
Liu, X., Yoo, C., Xing, F., Oh, H., El Fakhri, G., Kang, J.-W., & Woo*, J. (2022) · APSIPA Transactions on Signal and Information Processing · doi:10.1561/116.00000192 · Cited by 299
“Moreover, some of them only focus on limited application areas, such as visual data analytics (Wang and Deng, 2018; Csurka, 2017; Oza et al., 2021) or natural language processing (NLP) (Ramponi and Plank, 2020).”
BackgroundMulti-Modal 3D Object Detection in Autonomous Driving: A Survey and Taxonomy
Wang, L., Zhang, X., Song, Z., Bi, J., Zhang, G., Wei, H., Tang, L., Yang, L., Li, J., Jia, C., et al. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3264658 · Cited by 269
“Unlabeled data is prevalent in autonomous driving scenarios, and unsupervised learning can provide more robust learning of representations, which has been studied to some extent in similar tasks, such as 2D object detection [140], [141], [142], [143], [144], [145], [146], [147], [148].”
BackgroundDomain Adaptation: Challenges, Methods, Datasets, and Applications
Singhal, P., Walambe, R., Ramanna, S., & Kotecha, K. (2023) · IEEE Access · doi:10.1109/access.2023.3237025 · Cited by 234
“Surveys have been done on domain adaptation on specific computer vision tasks, e.g., semantic segmentation [294] and object detection [295].”
BackgroundCDTrans: Cross-domain Transformer for Unsupervised Domain AdaptationPreprint
Xu, T., Chen, W., Wang, P., Wang, F., Li, H., & Jin, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.06165 · Cited by 300
Contrastive Mean Teacher for Domain Adaptive Object Detectors
Cao, S., Joshi, D., Gui, L.-Y., & Wang, Y.-X. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02283 · Cited by 234
“For a comprehensive overview of this topic, one may refer to [28].”
Metadata
- Authors
- Oza, P., Sindagi, V. A., VS, V., & Patel, V. M.
- Affiliations
- Johns Hopkins University (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2024-06
- Volume
- 46
- Issue
- 6
- Pages
- 4018-4040
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4327852039
- Cited by
- 313
- References
- 204
- Citations by year
- 2026: 84 · 2025: 103 · 2024: 81
- FWCI
- 28.85
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- unsupervised domain adaptation, object detection, domain adaptation
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.