Unsupervised Domain Adaptation of Object Detectors: A Survey
Open accessThe DOI matches its Crossref record; 214 of the 214 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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 3×
“T HE success of deep learning has been greatly benefi-cial for various fields such as natural language processing[1],[2],[3],robotics[4],[5],[6],computervision[7],[8],[9], etc. Thisisespeciallyevidentinthecaseofcomputervi-sion,wheremajorityoftheprogresscanbelargelyattributed…”
BackgroundMethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
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
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
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 302
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 237
“For a comprehensive overview of this topic, one may refer to [28].”
Single-Domain Generalized Object Detection in Urban Scene via Cyclic-Disentangled Self-Distillation
Wu, A., & Deng, C. D. (2022) · 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/cvpr52688.2022.00092 · Cited by 195
Deep learning for computational cytology: A survey
Jiang, H., Zhou, Y., Lin, Y., Chan, R., Liu, J., & Chen, H. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102691 · Cited by 150
(2023) · International Journal of Food and Nutritional Sciences · doi:10.48047/ijfans/v11/i12/207 · Cited by 101
Liu, B., Yan, C., He, C., Lv, M., Wei, J., & Wu, L. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103491 · Cited by 93
Zhang, X., Zhang, S., Sun, Z., Liu, C., Sun, Y., Ji, K., & Kuang, G. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3559618 · Cited by 81
“Recently, researchers have proposed a domain adaptation method [20], [21], [22] in the field of machine learning.”
Qu, S., Chen, G., Zhang, J., Li, Z., He, W., & Tao, D. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19830-4_10 · Cited by 100
A comprehensive survey on domain adaptation for intelligent fault diagnosis
Wang, C., Wang, Z., Liu, Q., Dong, H., Liu, W., & Liu, X. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114109 · Cited by 101
CRetinex: A Progressive Color-Shift Aware Retinex Model for Low-Light Image Enhancement
Han, X., Zhang, H., Yi, X., & Ma, J. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02065-z · Cited by 70
“The enhanced images, which can depict clearer scene details, have the potential to promote the performance in subsequent high-level vision tasks such as sematic segmentation (Liu et al. 2021), object detection (Oza et al. 2023), recognition (Huang et al. 2022), and tracking (Gauglitz et al. 2011).”
Zhou, Z., Zhao, L., Ji, K., & Kuang, G. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3421512 · Cited by 73
“Domain-adaptive target detection and recognition effectively address this issue [36].”
BackgroundChen, C., Li, J., Zhou, H.-Y., Han, X., Huang, Y., Ding, X., & Yu, Y. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3179445 · Cited by 77
“DAOD [69], [70] aims to mitigate the distributional shift”
BackgroundSchwonberg, M., Niemeijer, J., Termöhlen, J.-A., schäfer, J. P., Schmidt, N. M., Gottschalk, H., & Fingscheidt, T. (2023) · IEEE Access · doi:10.1109/access.2023.3277785 · Cited by 75
“UDA for object detection is also an active research area [11] but is out of the scope of this survey.”
BackgroundMeta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning
Vibashan, V. S., Poster, D., You, S. O., Hu, S., & Patel, V. M. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00375 · Cited by 56
Self-citationDeng, B., Lu, Y., & Xu, J. (2024) · Ecological Informatics · doi:10.1016/j.ecoinf.2024.102546 · Cited by 51
Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment
Danish, M. S., Khan, M. H., Munir, M. A., Sarfraz, M. S., & Ali, M. (2024) · 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/cvpr52733.2024.01679 · Cited by 71
“Domain adaptive object detection: Several domain adaptive detection methods aim to reduce the pixel-level or feature-level gap between the source and target domain [36, 44].”
MethodFrom accuracy to approximation: A survey on approximate homomorphic encryption and its applications
Liu, W., You, L., Shao, Y., Shen, X., Hu, G., Shi, J., & Gao, S. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100689 · Cited by 43
Liu, X.-Y., Li, G., Zhou, X.-H., Liang, X., & Hou, Z.-G. (2025) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2025.3565754 · Cited by 36
“Currently, the UDA methods have also been widely applied in many other fields, such as fault diagnosis [55], [63], physical information estimation [53], classification tasks [56], [57], and object identification [54], [64].”
Zhao, S., Luo, Y., Zhang, T., Guo, W., & Zhang, Z. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3201628 · Cited by 41
PSDC: A Prototype-Based Shared-Dummy Classifier Model for Open-Set Domain Adaptation
Liu, Z., Chen, G., Li, Z., Kang, Y., Qu, S., & Jiang, C. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3228301 · Cited by 43
Domain Adaptation for Semi-Supervised Ship Detection in SAR Images
Chen, S., Zhan, R., Wang, W., & Zhang, J. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2022.3171789 · Cited by 34
Zhang, Y., Zhang, Y., Shi, Z., Fu, R., Liu, D., Zhang, Y., & Du, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3304684 · Cited by 44
“Then, the network is fine-tuned as a new training set, iteratively generating new pseudolabels that gradually approximate (converge to) the ground truth [17], [21], [22], [23], [45].”
BackgroundMethodInfluentialCOCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts
Mao, X., Chen, Y., Zhu, Y. P., Chen, D., Su, H., Zhang, R., & Xue, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00583 · Cited by 62
“Given the domain labels provided in COCO-O, one direct application is domain adaptation [60] or generalization [94] research.”
BackgroundG-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection
Wu, F., Gao, J., Hong, L., Wang, X., Zhou, C., & Ye, N. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i6.28410 · Cited by 51
Sun, J., Zheng, H., Diao, W., Sun, Z., Qi, Z., & Wang, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125444 · Cited by 34
S2R-ViT for Multi-Agent Cooperative Perception: Bridging the Gap from Simulation to Reality
Li, J., Xu, R., Liu, X., Li, B., Zou, Q., Ma, J., & Yu, H. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611572 · Cited by 43
Driver distraction detection via multi‐scale domain adaptation network
Wang, J., & Wu, Z. (2023) · IET Intelligent Transport Systems · doi:10.1049/itr2.12366 · Cited by 29
Unsupervised Domain-Adaptive Object Detection via Localization Regression Alignment
Piao, Z., Tang, L., & Zhao, B. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3282958 · Cited by 38
“We use three commonly used benchmarks with VGG16 [53] features to compare the performance of our method [55].”
MethodDomain-guided conditional diffusion model for unsupervised domain adaptation
Zhang, Y., Chen, S., Jiang, W., Zhang, Y., Lu, J., & Kwok, J. T.-Y. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.107031 · Cited by 35
Deep Learning for Low-Light Vision: A Comprehensive Survey
Zhao, Q., Li, G., He, B., & Shen, R. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3566647 · Cited by 39
“Oza et al. [36] and Li et al. [37] review the unsupervised domain adaptation methods and the source-free domain adaptation methods, respectively.”
DA-RAW: Domain Adaptive Object Detection for Real-World Adverse Weather Conditions
Jeon, M., Seo, J., & Min, J. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611219 · Cited by 38
“These methods adapt the model trained in the source domain of clear weather to the target domain of adverse weather by considering adverse weather as a factor contributing to the domain gap [18], [19].”
MethodUncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object DetectionPreprint
Hegde, D., Sindagi, V. A., Kilic, V., Cooper, A. B., Foster, M. A., & Patel, V. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.14651 · Cited by 31
Self-citationLi, J., Zhou, H., Lv, G., & Chen, J. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3541814 · Cited by 45
“Consequently, domain adaptation (DA) is a promising approach [10].”
Ghaffari, R., Helfroush, M. S., Khosravi, A., Kazemi, K., Danyali, H., & Rutkowski, L. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101912 · Cited by 25
An In-Depth Analysis of Domain Adaptation in Computer and Robotic Vision
Tanveer, M. H., Fatima, Z., Zardari, S., & Guerra-Zubiaga, D. A. (2023) · Applied Sciences · doi:10.3390/app132312823 · Cited by 30
Qi, G., Liu, K., Xie, M., Li, Y., & Ni, Q. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3487234 · Cited by 25
“To address this challenge, unsupervised domain adaptation (UDA), a branch of transfer learning, aims to minimize distribution discrepancies by learning common features between labeled source data and unlabeled target data [7], [8], [9].”
Wang, Y., Yan, J., Yang, Z., Zhang, W., Wang, J., Geng, Y., & Srinivasan, D. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3543239 · Cited by 24
“In addition, various DAN models have been developed for mechanical fault diagnosis, yielding excellent results [26], [26], [27], [28], [29], [30], [31], [32].”
Unsupervised Domain Adaptation: A Reality CheckPreprint
Musgrave, K., Belongie, S., & Lim, S.-N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.15672 · Cited by 33
Srivastav, V., Gangi, A., & Padoy, N. (2022) · Medical Image Analysis · doi:10.1016/j.media.2022.102525 · Cited by 25
Wi-SFDAGR: WiFi-Based Cross-Domain Gesture Recognition via Source-Free Domain Adaptation
Yan, H., Zhang, X., Huang, J., Feng, Y., Li, M., Wang, A., Ou, W., Wang, H., & Liu, Z. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3554228 · Cited by 33
“However, in real-world scenarios, there exist differences in the distributions of training and testing data [36], [37].”
Wang, K., Pu, L., & Dong, W. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3308896 · Cited by 23
“Unsupervised domain adaptation (UDA) methods [11], [12] apply the existing knowledge to the associated domain, which can effectively alleviate the reliance of object detection on labeled data and reduce the impact of domain shift.”
MethodAdaptive Ship Detection From Optical to SAR Images
Yuan, Y., Rao, Z., Lin, C., Huang, Y., & Ding, X. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3317321 · Cited by 22
“To alleviate the aforementioned issue, unsupervised domain adaptation (UDA) [1] has received extensive attention as a promising approach.”
BackgroundInfluentialLIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation
Xiao, Y., & Liao, H. (2023) · IET Image Processing · doi:10.1049/ipr2.13017 · Cited by 22
Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection
Hegde, D., & Patel, V. M. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00304 · Cited by 28
Self-citationNon-Convex Transfer Subspace Learning via Embedded Distribution Alignment
Luo, T., Liu, Y., Zhang, X., & Hou, C. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3671598 · Cited by 23
“Consequently, researchers have turned to unsupervised domain adaptation, as referenced in [4], [5], [6], and [7].”
Westerski, A., & Fong, W. T. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3637064 · Cited by 21
“Otherwise, other popular proposals for future work advocate increasing synthetic scene complexity, better photorealism and general efort towards Domain Adaptation [42] as supplementary to Domain Randomisation.”
BackgroundChen, J., Liu, L., Deng, W., Liu, Z., Liu, Y., Wei, Y., & Liu, Y. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3522807 · Cited by 24
“Toaddress these limitations, unsupervised cross domain object detection [3], [4], [5], [6], [7], [8], [9], [10], [11], [12] is proposed to adapt the detector from an annotated source domain to an unlabeled target domain.”
NIRNet: Noise Incentive Robust Network in Remote Sensing Object Detection Under Cloud Corruption
Zhang, P., Cheng, G., Lang, C., Xie, X., & Han, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3581342 · Cited by 33
“In particular, DA endeavors to narrow the disparity between clean and corrupted images by aligning their data distributions and learning domain-invariant feature representation from the source domain [31], [32], [33].”
Liu, S., Li, D., Song, H., Fan, C., Li, K., Wan, J., & Liu, R. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.07.017 · Cited by 23
Monitoring Outdoor Parking in Urban Areas With Unmanned Aerial Vehicles
Kim, S., Tak, Y., Barmpounakis, E., & Geroliminis, N. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3397588 · Cited by 21
“For a more comprehensive overview of the unsupervised domain adaptation, refer to the survey article by [59] and [60].”
BackgroundDu, Y., Fu, Z., & Liu, Q. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3444190 · Cited by 21
“Recent studies also extend the idea of domain alignment to encompass tasks spanning semantic segmentation [37], [41], [89]–[91] and object detection [92]–[95].”
BackgroundSemantic scattering graph structure alignment for cross-sensor SAR image target detection
ZHANG, X., Zhang, S. Z. S., Sun, Z., Liu, C., Sun, Y., Ji, K., & Kuang, G. (2026) · Chinese Journal of Aeronautics · doi:10.1016/j.cja.2026.104066 · Cited by 22
Tran, D. Q., Jeon, Y., Aboah, A., Bak, J., Park, M., & Park, S. (2024) · Journal of Construction Engineering and Management · doi:10.1061/jcemd4.coeng-15259 · Cited by 21
Wen, Z., Liu, J., Zhang, H., & Zuo, F. (2025) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2025.3567126 · Cited by 18
“As such, domain-adaptive object detection (DAOD) [10], [11], [12] has been proposed to mitigate this domain bias by strategies including adversarial learning (AT) [13], [14], [15], [16], mean-teacher self-training [17], [18], [19], and graph reasoning (GR) [20], [21] to generalize the detector to…”
DARTH: Holistic Test-time Adaptation for Multiple Object Tracking
Segù, M., Schiele, B., & Yu, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00891 · Cited by 30
“Several works [43] focus on the unsupervised domain adaptation problem for object detection, adopting traditional techniques such as adversarial feature learning [10, 51, 25, 56], image-to-image translation [72, 7, 49], pseudo-label self-training [27, 29, 50], and mean-teacher training [5, 14].”
BackgroundDomain Adaptive Detection of MAVs: A Benchmark and Noise Suppression Network
Zhang, Y., Deng, J., Liu, P., Li, W., & Zhao, S. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3370147 · Cited by 20
“MAV detection methods can be classified into two types: appearance-based methods [4], [34] and motion-based meth-ods [22], [35].”
Tian, H., Han, Y., Yang, P., Zhu, M., & Wu, D. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3337365 · Cited by 16
“To solve this problem, domain adaptation (DA) was widely applied for bearing RUL prediction [22], [23], [24].”
MethodLightweight Adaptive Feature De-Drifting for Compressed Image Classification
Peng, L., Cao, Y. H., Sun, Y., & Wang, Y. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3350917 · Cited by 65
“We perform multiple compressions on the dataset, and the quality factor of each compression is randomly chosen from 25, 18, 15, 10, and 7.”
BackgroundMethodChen, Z., Pan, Y., Ye, Y., Wang, Z., & Xia, Y. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3406447 · Cited by 17
“It uses labeled source domain images and unlabeled target domain images for training and is able to achieve competitive performance compared with fully-supervised fine-tuning approach [12], [13].”
FIOD-VUE: Focusing on Invariant Information in Object Detection of Varying Underwater Environment
Xie, Z., Yang, M., Shen, M., Qiu, Y., & Wang, X. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3417000 · Cited by 19
“interaction, and self-checkout convenience stores [1].”
A Structure-Preserving and Illumination-Consistent Cycle Framework for Image Harmonization
Cai, X., Shi, Q., Gao, Y., Li, S., Hua, W., & Xie, T. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3260620 · Cited by 19
USB: Universal-Scale Object Detection BenchmarkPreprint
Shinya, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.14027 · Cited by 19
“To avoid performance drops in target domains without laborintensive annotations, many studies have tackled domain adaptation of object detection [51].”
BackgroundMethodThree New Validators and a Large-Scale Benchmark Ranking for Unsupervised Domain AdaptationPreprint
Musgrave, K., Belongie, S., & Lim, S.-N. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.07360 · Cited by 21
Temporal Attention Source-Free Adaptation for Chemical Processes Fault Diagnosis
Xiao, Y., Shi, H., Song, B., Tao, Y., Tan, S., & Wang, B. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3312409 · Cited by 15
Uncertainty-guided alignment for unsupervised domain adaptation in regression
Nejjar, I., Frusque, G., Forest, F., & Fink, O. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.112143 · Cited by 17
Variational Information Bottleneck for Cross Domain Object Detection
Chen, J., Deng, W., Peng, B., Liu, T., Wei, Y., & Liu, L. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00381 · Cited by 17
“Thus, cross domain object detection [1]–[4] has aroused great interest in recent years.”
BackgroundAbdulkareem, I. M., AL-Shammri, F. K., Khalid, N. A. A., & Omran, N. A. (2024) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v20i05.47171 · Cited by 13
Confidence-Driven Region Mixing for Optical Remote Sensing Domain Adaptation Object Detection
Liu, C., Dong, Y., Zhang, Y., & Li, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3417610 · Cited by 14
“Since then, the task has continued to develop and can be classified into three categories [37].”
BackgroundNighttime image semantic segmentation with retinex theory
Sun, Z., Zhu, H., Xiao, X., Gu, Y., & Xu, Y. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105149 · Cited by 15
Zhang, G., Wang, L., & Chen, Z. (2024) · Remote Sensing · doi:10.3390/rs16152722 · Cited by 14
Fully Test-time Adaptation for Object Detection
Ruan, X., & Tang, W. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00110 · Cited by 26
“Unsupervised domain adaptation (UDA) methods [5, 20, 23, 25] require both labeled source data and unlabeled target data.”
Illumination-Guided progressive unsupervised domain adaptation for low-light instance segmentation
Zhang, Y., Guo, J., Yue, H., Zheng, S., & Liu, C. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106958 · Cited by 14
WCAL: Weighted and center-aware adaptation learning for partial domain adaptation
Zhang, C., Hu, C., Xie, J., Wu, H., & Zhang, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107740 · Cited by 12
AD-Aligning: Emulating Human-Like Generalization for Cognitive Domain Adaptation in Deep Learning
Li, Z., Wan, B., Mu, C., Zhao, R., Qiu, S., & Yan, C. (2024) · International Conference on Electronic Communication and Artificial Intelligence (ICECAI) · doi:10.1109/icecai62591.2024.10675013 · Cited by 12
“Researchers have employed various strategies to tackle the challenge of domain shift, where the distribution of data differs between training and testing phases [3].”
BackgroundProgressive Critical Region Transfer for Cross-Domain Visual Object Detection
Wang, X., Jiang, P., Li, Y., Hu, M., Gao, M., Cao, D., & Ding, R. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3382841 · Cited by 11
“Thanks to those effective schemes exploited for UDA, adapting object detectors to a real-world application scenario is arousing extensive research interests gradually [35].”
BackgroundPrototype-guided domain adaptive one-stage object detector for defect detection
Ye, B., Lai, J., Xie, X., & Zhu, J. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102618 · Cited by 11
Liao, R., Zhang, Y., Wang, H., Lu, L., Chen, Z., Wang, X., & Zuo, W. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13501 · Cited by 11
“While this approach is suitable for simpler tasks, it struggles to completely eliminate the domain gap between simulated and real datasets (Oza et al., 2023).”
Li, Z., Yao, Y., Quan, Z., Qi, L., Feng, Z., & Yang, W. (2023) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2023.3343878 · Cited by 12
DomAda-FruitDet: Domain-Adaptive Anchor-Free Fruit Detection Model for Auto Labeling
Zhang, W., Zheng, C., Wang, C., & Guo, W. (2023) · Plant Phenomics · doi:10.34133/plantphenomics.0135 · Cited by 12
Adaptive Graph Learning With Semantic Promotability for Domain Adaptation
Zheng, Z., Teng, S., Teng, L., Zhang, W., & Wu, N. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3507534 · Cited by 11
Fine-grained gaze estimation based on the combination of regression and classification losses
Abdelrahman, A. A., Hempel, T., Khalifa, A., & Al-Hamadi, A. K. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05778-3 · Cited by 10
CATALOG: A Camera Trap Language-Guided Contrastive Learning Model
Santamaria, J. D., Isaza, C., & Giraldo, J. H. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00124 · Cited by 16
“Despite the success of FMs, adapting them to specific domains that differ significantly from the original training data remains a challenging task [4, 22, 37].”
Wei, R., Yang, L., Li, X., Zhu, C., Zhang, L., Wang, J., Liu, J., Zhu, L., & Zhou, C. (2025) · Remote Sensing of Environment · doi:10.1016/j.rse.2025.115051 · Cited by 10
Tang, R., Chen, Y., Gao, D., Gao, J., & Hao, S. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2025.123771 · Cited by 10
Gated image-adaptive network for driving-scene object detection under nighttime conditions
Wang, Y., Lu, Y., & Qiu, Y. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01589-1 · Cited by 11
“This issue can also be regarded as an unsupervised domain adaptation (UDA) strategy [18, 19].”
EventFly: Event Camera Perception from Ground to the Sky
Kong, L., Lu, D., Xu, X., Ng, L. X., Ooi, W. T., & Cottereau, B. R. (2025) · 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/cvpr52734.2025.00145 · Cited by 24
“Conventional domain adaptation methods commonly used for frame-based sensors are not well-suited to handle the distinct spatial-temporal nuances of event camera data, which demand tailored alignment strategies [48, 50, 60, 78].”
Zhang, Y., Yang, B., & Zhao, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111350 · Cited by 9
Training marine species object detectors with synthetic images and unsupervised domain adaptation
Doig, H., Pizarro, O. R., & Williams, S. B. (2025) · Frontiers in Marine Science · doi:10.3389/fmars.2025.1581778 · Cited by 12
Transformer-driven multi-scale contextual alignment for robust E-nose drift compensation
Sun, J., Dong, M., Lu, F., Wang, Z., Zhu, J., Wang, Y., Zheng, L., & Zhao, F. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114136 · Cited by 9
Information filtering and interpolating for semi-supervised graph domain adaptation
Qiao, Z., Xiao, M., Guo, W., Luo, X., & Xiong, H. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110498 · Cited by 15
OSSID: Online Self-Supervised Instance Detection by (And For) Pose Estimation
Gu, Q. L., Okorn, B., & Held, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3145488 · Cited by 12
“[39] for a comprehensive survey on unsupervised domain adaptation of object detection.”
BackgroundSupervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyond
Vu, T., Sun, B., Yuan, B., Ngai, A., Li, Y., & Frahm, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i6.28335 · Cited by 14
“However, state-of-the-art detectors still suffer from poor generalization abilities and struggle with data outside their training distribution, especially under domain shifts (Li et al. 2020; Oza et al. 2021).”
BackgroundAdaptive Distraction Recognition via Soft Prototype Learning and Probabilistic Label Alignment
Liu, Y., Du, S., Han, H., Chen, X., Zeng, W., & Tian, Z. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3444006 · Cited by 8
“UDA, or unsupervised domain adaptation, has gained significant attention in the research community for its goal of transferring knowledge from a label-rich source domain to an unlabeled target domain [9], [10], [22], [23], [24].”
BackgroundŞtefan, V., Stark, T., Wurm, M., Taubenböck, H., & Knight, T. M. (2025) · Scientific Reports · doi:10.1038/s41598-025-16140-z · Cited by 9
Cross-Domain Object Detection with Hierarchical Multi-Scale Domain Adaptive YOLO
Zhu, S., Zhu, P., Wu, Y., & Qiao, W. (2025) · Sensors · doi:10.3390/s25175363 · Cited by 9
“Therefore, researchers pay more and more attention to cross-domain detection techniques [14].”
Davari, S., Kim, D., & Tohidifar, A. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106562 · Cited by 9
Li, Y., Ou, X., Liu, S., Zhao, J., Xue, L., Liu, C., Zhu, B., Yan, S., Wang, S. D., Wei, Z., et al. (2026) · Science Advances · doi:10.1126/sciadv.adz0228 · Cited by 10
“At present, machine learning–based intelligent recognition technology has brought advances in x-ray imaging, enabling lesion area identification in medical diagnostics and defect detection in the semiconductor industry ( 8 – 12 ).”
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.