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
Items 201–300 of 369
Datasets, Metrics, Benchmarks and Future Research in Autonomous Driving: A Review
Li, Y., Teng, S., Wu, Z., Wang, J., Liu, M., Xuanyuan, Z., & Chen, L. (2026) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2025.125957 · Cited by 2
He, W., Zhang, Y., & Wang, Z. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00314 · Cited by 6
“( Bottom ) We retrieve auxiliary data from LAION-400M [65] in an annotation-free manner and adaptively construct it with progressively changing distributions towards the target data distribution. bution discrepancies between training and downstream task datasets [23, 26, 43, 44, 59, 82].”
High-Frequency Information Supported Domain Adaptation for Cross-Domain Object Detection
Yang, Y., Shao, C., Xie, Z., Shu, X., & Yu, H. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3705381 · Cited by 2
“This is mainly due to domain shift, wherein the distribution of test-time images largely deviates from that of the training data due to real-world variations in illumination, weather, season, and other factors [6], [7], [8].”
OnDA-DETR: Online Domain Adaptation for Detection Transformers with Self-Training Framework
Suzuki, S., Yamane, T., Makishima, N., Suzuki, K., Ando, A., & Masumura, R. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222353 · Cited by 2
“Most domain adaptation research focuses on unsupervised domain adaptation [11], in which labeled source domain and unlabeled target domain data are both accessible during training.”
BackgroundKwon, Y. H., Park, S., Luan, T., Oh, S., & Heo, J. (2024) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784485248.062 · Cited by 2
Unsupervised Cross-domain Object Detection via Multiple Domain Randomization
Luo, F., Liu, J., Ho, G. T. S., & Yan, K. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580650 · Cited by 3
“In order to solve the above problems, the Unsupervised Domain Adaptation (UDA)[1] method based on transfer learning is widely studied.”
MethodAdaptive Adversarial Self-Training for Semi-Supervised Object Detection in Complex Maritime Scenes
Feng, J., Tian, L., & Li, X. (2024) · Mathematics · doi:10.3390/math12152348 · Cited by 2
“However, these methods used different pipelines of data augmentation, such as strong–weak augmentations, for labeled data and unlabeled data, which may produce distribution bias between labeled data and unlabeled data [14].”
DADETR: Feature Alignment-based Domain Adaptation for Ship Object Detection
Wu, J., & Meng, H. (2024) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma61710.2024.10633006 · Cited by 2
“…images are influenced by factors such as acquisition viewpoints, object appearances, background styles, lighting conditions, image quality, etc. [1], as show in Fig.1, which lead to significant differences between the data distribution of the test dataset and the training dataset, which we…”
BackgroundA Transferable Ensemble Additive Network for Interpretable Prediction of Key Performance Indicators
Su, C., Peng, X., Yang, D., Lu, R., Huang, H., & Zhong, W. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3472806 · Cited by 2
“In particular, UDA is essentially a class of methods close to transductive TL for the scenario where source domain labels are available and target domain labels are not [17], [18], [19], [20], with a focus on reducing the distributional discrepancies between domains.”
BackgroundMicro-community domain adaptation
Zheng, Z., Teng, S., Teng, L., Wu, N., & Zhang, W. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.111270 · Cited by 2
Computer Vision for Damage Detection in Cars Images
Elgargouh, Y., Ghazali, M., Louhdi, M. R. C., Zemmouri, E. M., & Behja, H. (2024) · International Conference on Advanced Communication Technologies and Networking (CommNet) · doi:10.1109/commnet63022.2024.10793245 · Cited by 2
“This capability accelerates the training process, as the models can converge more quickly to optimal performance on the target dataset [19].”
Wu, A., Fan, K., Zheng, B., Zhang, A., Li, A., & Wang, M. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107763 · Cited by 2
SADA: Semantic Adversarial Unsupervised Domain Adaptation for Temporal Action Localization
Pujol-Perich, D., Clapés, A., & Escalera, S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00895 · Cited by 3
“These anchors are extracted with a multi-resolution architecture [48] that we couple with a novel adversarial loss that improves the limitations of existing UDA works.”
Lan, B., Krijnen, G. J. M., Stramigioli, S., & Niu, K. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3562072 · Cited by 2
“Similar techniques have been successfully used in various fields, such as improving model generalization across datasets with domain shifts [40] and unsupervised adaptation for learning representations under different conditions [41].”
Key Design Choices for Double-Transfer in Source-Free Unsupervised Domain AdaptationPreprint
Maracani, A., Camoriano, R., Maiettini, E., Talon, D., Rosasco, L., & Natale, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2302.05379 · Cited by 2
“, 2019], and also for other tasks such as object detection [Oza et al., 2021] and semantic segmentation [Toldo et al.”
BackgroundConformal Test Martingale-Based Change-Point Detection for Geospatial Object Detectors
Wang, G., Lu, Z., Wang, P., Zhuang, S., & Wang, D. (2023) · Applied Sciences · doi:10.3390/app13158647 · Cited by 1
de Andrade, M. L. S. C., Souza, A., Oliveira, B. A. S., Starling, M. C. V. M., Amorim, C. C., & Santos, J. (2024) · International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP) · doi:10.5220/0012574500003660 · Cited by 1
“Therefore, the scientific community has sought alternatives to the problem of scarcity of labeled data to enable and expand the use of techniques in these challenging situations (Masud, 2012), (Li et al., 2020), (Oza et al., 2023).”
BackgroundDETECTION AND RECOGNITION OF IRAQI LICENSE PLATES USING CONVOLUTIONAL NEURAL NETWORKS
Abbas, M., & Mohammed, Z. M. (2025) · Science Journal of University of Zakho · doi:10.25271/sjuoz.2025.13.1.1344 · Cited by 1
Domain adaptive YOLO based on image style selection and synergistic domain classifier
Zhou, Y., & Qian, H. (2025) · Displays · doi:10.1016/j.displa.2025.102967 · Cited by 1
UVPose: A Real-Time Key-Point-Based Skeleton Detection Network for a Drone Countermeasure System
Yao, B., Wang, W., Wang, Z., & Song, Q. (2025) · Drones · doi:10.3390/drones9030214 · Cited by 1
“However, with advances in object detection algorithms, the detection phase is no longer the bottleneck [18,19].”
DPAC: a dual-path domain adaptive fasteners detection method based on adaptive cutmix strategy
Wang, J., Chen, C., Dai, C., Liu, K., & Zheng, P. (2025) · Measurement · doi:10.1016/j.measurement.2025.118315 · Cited by 1
Adaptive Ternary Division with VLM Knowledge for Domain Adaptation of Black-Box Predictors
Zeng, Z., Zhang, Y., & Wang, J. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9986-5_41 · Cited by 1
CUOM: A causal unbiased optimization method for federated domain generalization
Wen, M., Han, K., Li, D., Cai, Q., & Shen, H. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114249 · Cited by 3
Liu, M., Tong, Z., Jin, X., Zhang, Z., Liu, X., Luo, J., & Li, Z. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3611499 · Cited by 2
“The performance of various algorithms in intelligent transportation is affected by image modality differences, for which image translation serves as an effective solution [41].”
Cross-domain Few-shot Object Detection with Multi-modal Textual Enrichment
Shangguan, Z., Seita, D., & Rostami, M. G. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02839-7 · Cited by 4
“As illustrated in Figure 2, object detection methods, including MM-OD approaches, experience significant performance degradation when trained and evaluated on datasets with distinct source and target domains.”
TIGNet: Text–Image Guided Network for Airport Runway Subsurface Defect Detection
Li, N., Pan, Y., Li, H., Ji, L. J., Gui, Z., Koshekov, K., & Song, D. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3620993 · Cited by 1
“This evaluation design, compared to commonly used metrics in cross-domain object detection studies [39], [40], [41], places greater emphasis on the degradation of a model relative to its own baseline performance.”
Context Aware Grounded Teacher for Source Free Object Detection
Ashraf, T., Manna, R., Purkayastha, P. S., Tariq, T., & Bashir, J. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02905-0 · Cited by 1
“Source-free domain Adaptation ( SFDA ) has received significant attention for the image classification task in recent years [127, 139, 117, 57, 30, 50, 128].”
Influentiald-MAR: Deep Metal Artifact Reduction via Diffusion-Driven Domain Transformations
Guo, Y., Zeng, Z., Song, Y., Lu, M., Zhang, Y., He, J., Wen, Z., Zeng, D., Bian, Z., Wang, Y., et al. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3636878 · Cited by 1
Unsupervised domain adaptive object detection via discriminative instance teacher
Ge, Y., Liu, H., Hu, Y., Zhao, J., Du, J., Shang, E., & Niu, Z. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130656 · Cited by 1
SwinMR: A Mutual Refinement Enhanced SwinTrack Framework
Zhao, S., Yang, C., & Fu, Y. (2025) · Applied Sciences · doi:10.3390/app152413070 · Cited by 1
Hard-Label Black-Box Adversarial Attacks for Implicit Scene Interactions
Liang, M., Wang, C., Liang, S., Liu, A., Cao, Y., Li, Q., Liu, Z., Yang, L., & Cao, X. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3615399 · Cited by 1
“Restrictions apply. component in visual instance understanding [1].”
Wang, Q., Zhengyang, Y. U., Liu, R., Xingpeng, P. E. N. G., Yang, X., & Xiuwen, H. E. (2025) · Fishes · doi:10.3390/fishes11010021 · Cited by 1
“A two-stage transfer learning pipeline was established to bridge the gap between the above-water and underwater domains to address the challenges of limited underwater training samples and domain discrepancies, which often lead to slow convergence and over-fitting [27–29].”
Geng, H., Fang, L., Wang, Y. J., Liu, Z., & Fan, Z. (2026) · IET Image Processing · doi:10.1049/ipr2.70294 · Cited by 1
Domain Adaptation for Object Detection Based on Domain-Aware Prompting in Remote Sensing Imagery
Zhang, X., Yao, X., Cheng, G., & Han, J. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3661721 · Cited by 2
“DA employs labeled data from the source domain to facilitate model training, thereby enabling adaptation to the target domain and yielding enhanced performance without the necessity of target-domain annotations [34], [35], [36], [37].”
Unsupervised Domain Adaptation for Fish Counting: From Optical to Forward-Looking Sonar Images
Liu, H., & Ma, X. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3665824 · Cited by 2
“UDA techniques have demonstrated strong capabilities in various tasks, such as image classification [47], [48], semantic segmentation [49], [50], and object detection [51], [52].”
SSRT-DETR: Domain-Adaptive Semi-Supervised Detector
Zhang, W., Zhou, D., Xie, W., & Wang, W. (2026) · Sensors · doi:10.3390/s26051539 · Cited by 1
Guo, X., Gao, F., Li, K., Lin, Q., Liu, J., Tong, L., Xiao, X., Xie, L., & Zhao, Y. (2026) · Nuclear Instruments and Methods in Physics Research Section A Accelerators Spectrometers Detectors and Associated Equipment · doi:10.1016/j.nima.2026.171506 · Cited by 1
“Similar unsupervised techniques have demonstrated strong cross-domain generation capabilities in fields such as computer vision [17–21], medical image synthesis [22, 23], and artistic style transfer [15, 24, 25].”
RShDet: An Adaptive Spectral-Aware Network for Remote Sensing Object Detection Under Haze Corruption
Zhang, W., Wang, Y., Yang, H., & Mao, X. (2026) · Remote Sensing · doi:10.3390/rs18071020 · Cited by 1
Unsupervised Domain Adaptation-Based Cross-Type Deepfake Image Detection
Wang, Q., Wang, X., Liu, Z., Bai, N., Zhao, M., & Pang, S. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3685445 · Cited by 3
“Among these fields, computer vision tasks such as object detection [50], [51], [52], pedestrian re-recognition [53], [54], image generation [55], [56] and semantic segmentation [55], [56] are particularly prevalent.”
Peng, Z., Qi, Y., Wang, Z., Wang, Y., 刘宗培, & Cao, X. (2026) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2026.114274 · Cited by 2
MMTF-DTI: Drug–target interaction prediction via multimodal feature extraction and dynamic fusion
Zeng, P., Li, Z., Tang, X., Meng, Y., Zhang, Z., Cui, F., Jiang, J., & Xu, J. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.105069 · Cited by 1
Unsupervised Domain Adaptation for EEG-Based Emotion Recognition in Virtual Environments
Babu, N., Mathew, J., Satija, U., & Vinod, A. P. (2026) · SN Computer Science · doi:10.1007/s42979-026-05192-1 · Cited by 1
Lightweight Source-Free Unsupervised Domain Adaptation for Object Detector Using Stereo Vision
Ninh, P. P., & Kim, H. (2026) · IEEE Access · doi:10.1109/access.2026.3706740 · Cited by 1
“Recent frameworks also include DEtection TRansformer (DETR) [27], [43] but there is a lack of support for the emerging YOLO detector family [39].”
InfluentialOnce for All: An End-to-End Paradigm for VLM-Based Domain-Generalized Object Detection
Zhang, P., Yuan, X., Li, C., Han, J., & Cheng, G. (2026) · doi:10.1109/cvprf71909.2026.00656 · Cited by 2
“Even so, training on the elaborate dataset leads to a dilemma in open-domain generalization [26, 32, 49, 57], where the primary Figure 1.”
Niu, Y., Cheng, W., Lai, Y. F., Zhang, H., Cao, M., Cao, K., & Fan, S. (2023) · IEEE Access · doi:10.1109/access.2023.3297265 · Cited by 1
Improving Rare Classes on nuScenes LiDAR segmentation Through Targeted Domain Adaptation
Rajendran, V., Tang, C., & van Paasschen, F. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00018 · Cited by 4
Qi, H., Chen, W., & Deng, X. (2023) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus58632.2023.10318282 · Cited by 1
“Therefore, conducting cross-domain object detection by utilizing visible-light datasets that are easy to acquire and annotate (such as drone aerial image datasets) for remote sensing image target domains has significant practical importance [1].”
BackgroundEnhancing Robot Perception with Real-World HRI
Wozniak, M. K. (2024) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3610978.3638363 · Cited by 1
“Another way is to use Unsupervised Domain Adaptation (UDA) methods [18].”
MethodOtaño, N. B. N., Pincheira, E. P., Moritan, V. C., & Llorens, M. (2024) · Historical Biology · doi:10.1080/08912963.2024.2408804 · Cited by 1
“…databases accessing a wide range of valuable data (GBIF, Palynodata, Paleodb, Globalfungi.com, FUNguild, etc.) and process high volumes of information, with an open-source cross-platform such as QGIS increasing data reuse and reproducibility worldwide (Baxevanis and Bateman 2015; Oza et al. 2023).”
Guangzhi, 张. Z., Huimin, 李. L., & Xuning, 宋. S. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop240983 · Cited by 1
Design of a Lung Lesion Target Detection Algorithm Based on a Domain-Adaptive Neural Network Model
Liu, X., Liu, W., & Wu, A. (2025) · Applied Sciences · doi:10.3390/app15052625 · Cited by 1
Navigating Adverse Weather: An Exploration of YOLOv8's Object Detection in Fog
Haris, M., Iqbal, M., Malik, M. O., Bokhari, S. A. S., Alahmari, S., & Azam, F. (2024) · International Conference on Engineering and Emerging Technologies (ICEET) · doi:10.1109/iceet65156.2024.10913626 · Cited by 1
“For example, the Foggy Cityscapes is a key dataset since it augments the original Cityscapes images by overlaying realistic fog to make it a standard instrument for improving object detection in poor weather conditions [19, 21].”
Li, S., Yan, F., Li, Z., Hu, Q., Xu, S., & Liu, S. (2025) · IEEE Access · doi:10.1109/access.2025.3558409 · Cited by 1
“Semi-supervised or unsupervised learning combines a small amount of labeled data with a large amount of unlabeled data for training [42], which can reduce computational resource consumption to some extent.”
Learning transferable representations by topic guided graph adversarial network
Wang, Z., Xin, Z., Chen, C., Zhang, H., Huang, Y., Li, Y., Liu, H., & Chen, B. (2025) · Signal Processing · doi:10.1016/j.sigpro.2025.110118 · Cited by 1
Chen, X., Lv, J., Wang, Z., Qin, G., & Zhou, Z. (2025) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2025.104869 · Cited by 1
High-Quality Pseudo-Label Generation Based on Visual Prompt Assisted Cloud Model Update
Xu, X., Zhang, Q., Yang, J., Lian, Z., Yan, J., Ding, Z., & Jiang, S. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228573 · Cited by 1
“To enhance the quality, un-supervised domain adaptation techniques [25] are employed, aiming to minimize the following objective function to adapt f t : where L S denotes the source domain loss function, and D represents the inter-domain distance.”
Miyaki, S., Morikura, T., Nishimoto, S., Tokuoka, Y., Yamada, T., & Funahashi, A. (2026) · IEEE Access · doi:10.1109/access.2026.3657610 · Cited by 1
Correctly Evaluating Machine Learning Algorithms
Musgrave, K. (2023) · eCommons (Cornell University) · doi:10.7298/8jjj-dg74 · Cited by 1
Data-Centric Learning Method for Synthetic Data Augmentation and Object Detection
Park, Y., Kim, H., Park, Y. J., Lee, C., & Lee, J.-S. (2022) · JOIV International Journal on Informatics Visualization · doi:10.30630/joiv.6.1-2.939 · Cited by 1
“Domain adaptation studies for object detection are classified into several main categories [2]: image-to-image translation, adversarial feature learning, pseudo-label-based self-training, domain randomization, and graph reasoning.”
BackgroundCardace, A., Conti, A., Ramirez, P. Z., Spezialetti, R., Salti, S., & Stefano, L. D. (2023) · IEEE Access · doi:10.1109/access.2023.3304542 · Cited by 1
“such as classification [3], object detection [4] and 2D semantic segmentation [5].”
MethodGao, D., Yang, J., Wang, Q., & Wu, J. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4587781
Joint Distribution Alignment and Transfer Subspace Learning for Unsupervised Domain Adaptation
Liu, Y., & Luo, T. (2023) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis59572.2023.10262974
Gao, D., Yang, J., Wang, Q., & Wu, J. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4618559
Incremental Domain Learning for Surface Quality Inspection of Automotive High Voltage Battery
Shirazi, M., Safronov, G. S., & Risk, A. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00245
“DA is one of the primary situations in real-world applications, which is reviewed [18] within the frameworks of unsupervised [6], semi-supervised [19], weakly supervised DA [20].”
BackgroundUnsupervised domain adaptation approaches for person localization in the operating rooms
Srivastav, V. (2021) · theses.fr (ABES) · doi:10.70675/bba4f002z471bz4597zbda9zd6b68a13b76a · Cited by 1
Domain-adaptive Object Detection with Dynamic Mosaic and Consistent Learning
Gao, D., & Yang, J. (2023) · International Academic Exchange Conference on Science and Technology Innovation (IAECST) · doi:10.1109/iaecst60924.2023.10503445
“In order to solve this problem, domain-adaptive object detection has become a key research direction [2], especially in the applications where the training and deployment scenarios differ significantly.”
BackgroundUsmani, U. A., Jaafar, J., Azis, I. A., Watada, J., & Usmani, A. Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4896025
Learning Frequency and Structure in UDA for Medical Object Detection
Wang, L., Zhang, X., He, G., Tan, Y., Li, S., Pu, B., Jin, Z., Sha, W., & Dong, X. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8496-7_36
Maglo, A., & Audigier, R. M. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78447-7_8 · Cited by 1
Adapting Complex Event Detection to Perceptual Domain Shifts
Wang, B., Briseno, J. D. G., Han, L., Phillips, H., Craighead, J. D., Purman, B., Kaplan, L., & Srivastava, M. B. (2024) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom61039.2024.10773796 · Cited by 1
Prospective domain adaptation for longitudinal data
Park, S., Yeon, J., Lee, D. A., Son, S. J., Woo, H. G., & Shin, H. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112879
Adaptive Target-Consistency Entity Matching Algorithm Based on Semi-Supervised Learning
Yuedanni (2024) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia63733.2024.10808744
STC: Student-Teacher Collaborative Model for Multi-Target Domain Adaptation
Jiayi, X., Yu, J., Yixin, W., & Shijia, H. (2024) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip64812.2024.10873765
“Domain randomization : As mentioned by Poojan et al.[4], this method uses domain randomization strategy to create multiple stylized versions of source domain images to train the detector model, so that the model is not biased to any one style, so that it can be generalized better.”
Aerial Remote Sensing Object detection using Unsupervised Domain Adaptive
Youssef, Y. B., Lyaqini, S., Fakhar, K., & Abdelmounim, E. (2024) · Statistics Optimization & Information Computing · doi:10.19139/soic-2310-5070-1749
“As a result, UDA offers a solution to this problem, which we have provided to detect and localize objects in ARSI as unlabeled target domain [6, 7].”
Zhou, Y., Shi, M., Chen, B., Ding, C., Shen, C., & Zhu, Z. (2024) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd64214.2024.10920328
Federated Hypothesis Transfer for Decentralized Multi-Source Domain Adaptation
Zhang, Y., & Song, L. (2024) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn63567.2024.00092
Acoustic Simulated Sonar Data and Neural Networks for Marine Mine Detection
Peltier, C. L., Lopez, S. B., Gall, Y. L., Haugeard, J., Hassan, D., Malkasse, J., Burlet, N., & Mari, Z. (2025) · MTS/IEEE OCEANS Conference (OCEANS) · doi:10.1109/oceans58557.2025.11104554 · Cited by 1
“Domain adaptation is a method used to enhance the performance of a machine learning model when applied to a different domain or environment from the one it was trained on [22].”
Generalized Object Detection in the Infrared Domain Based on Common-Representation Learning
Liu, D., Shi, Z., & Liu, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04546-1_17
Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
Xu, X., Yang, J., Zhang, Q., Lian, Z., Ding, Z., & Jiang, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04558-4_50
Review of research progress on self-training for object detection in unmanned system perception
Yu, P., Zhang, X., Sun, H., & Zheng, N. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0095
Sunil Kumar Aithal, S., & Acharya, S. (2025) · International Conference on Inventive Systems and Control (ICISC) · doi:10.1109/icisc65841.2025.11187970
“Autoencoder, popular generative adversarial networks (GANs), domain randomization, mean-teacher (semi-supervised), pseudo-labeling strategy (semi-supervised), graph guided reasoning and adaptive image-to-image translation schemes have been employed for adaptive unsupervised OD task [8].”
DLLM: Enhancing Open-World Object Detection with Dynamic Learning and Large Models
Huang, Y., Xi, X., & Luo, R. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209937 · Cited by 2
Exploring the Use of Synthetic Data to Improve Pedestrian Detection in CNN
Montanha, R., & Musse, S. R. (2025) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi67909.2025.11223354 · Cited by 1
Domain Adaptation for Camera-Specific Image Characteristics using Shallow Discriminators
Gruber, M., Seiler, J., & Kaup, A. (2025) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip67698.2025.11396816
“Therefore, domain gaps are commonly addressed by Domain Adaptation (DA) [6].”
Sayyad, F. Z., Pettersson, T., Mousavirad, S. J., Shallari, I., & O’Nils, M. (2025) · Machine Learning with Applications · doi:10.1016/j.mlwa.2025.100806
Knowledge Transferability for Data-Efficient Deep Learning
Maracani, A. (2024) · CINECA IRIS Institutial Research Information System (University of Genoa) · doi:10.15167/maracani-andrea_phd2024-04-12 · Cited by 1
Beikrauterkennung in landwirtschaftlichen Bildern mittels Deep Learning
Genze, N., Grimm, D. G., & München, T. U. (2025) · mediaTUM (Technical University of Munich)
CoDS: Enhancing Collaborative Perception in Heterogeneous Scenarios via Domain Separation
Han, Y., Zhang, H., Zhang, H., Ding, C., Cao, Y., & Li, Y. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3622937 · Cited by 2
“Domain adaptation [48], [49], [50] addresses domain shift challenges when transferring knowledge across different domains.”
Dynamic IoU Thresholding for Test-Time Adaptive Object Detection
Wan, K., Zheng, J., & Wang, M. N. (2025) · International Conference on New Trends in Computational Intelligence (NTCI) · doi:10.1109/ntci67886.2025.11308184
“Traditional domain adaptation meth-ods, such as Unsupervised Domain Adaptation (UDA) [1][2] and Source-Free Domain Adaptation (SFDA) [3][4], aim to mitigate this issue but rely on strong assumptions: the target domain must be fixed and known in advance, and a representative target dataset is…”
A Unified Object Detection Method in Drone View With Degradation‐Aware and Domain Adaptive Modeling
Wu, L., & Wang, S. (2026) · Engineering Reports · doi:10.1002/eng2.70597 · Cited by 1
Ceiling Hazardous Object Inspection Robot for Counter-terrorism Security Check
Lee, S., Koh, D., Lee, M., Song, H., Pyo, J., Suh, J., & Kim, M. (2026) · Journal of the Korean Society for Precision Engineering · doi:10.7736/jkspe.025.047
Hu, H., Jin, H., Liu, S., & Fang, H. (2025) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin64977.2025.11279627
“This method enhances model generalization capability without requiring target domain labels by mining shared features between source and target domains, significantly reducing annotation costs while improving cross-domain diagnostic reliability[8].”
de Filippis, R., & Foysal, A. A. (2026) · OALib · doi:10.4236/oalib.1114445
Text Adversarial Examples Attack and Defense Framework Based on Generative Adversarial Networks
Ma, S., Liu, P., Zhai, Y., Yu, M., Yang, W., & Zhang, J. (2025) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1109/dsins68311.2025.11329875
“DNNs have achieved massive success in image processing, such as object detection [3] and face recognition [4].”
Wang, Y.-K., Pan, T.-M., & Chen, T.-Y. (2026) · Scientific Reports · doi:10.1038/s41598-025-30664-4
Gu, L., Huang, W., & Du, G. (2025) · International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC) · doi:10.1109/sdpc68151.2025.11347744
“Driven by continuous breakthroughs of deep learning in image recognition and NLP [4,5], an increasing body of research has focused on employing classical deep models, such as CNNs and RNNs, for bearing fault diagnosis.”
A Wave Is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series
Ma, X., Hong, X., Li, W., & Lu, S. (2026) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3788674
A machine learning based approach for value stream map digitization
Mitschke, F., Spieckermann, S., & Metternich, J. (2026) · Procedia CIRP · doi:10.1016/j.procir.2026.01.026
Label Semantic and Sample Relationship Collaborative Learning for Domain Adaptation
Wang, Z., Teng, S., Zheng, Z., Zhang, W., & Kang, P. (2025) · IEEE Smart World Congress (SWC) · doi:10.1109/swc65939.2025.00147
“Nowadays, in some fields such as medical image processing and object detection [1], [2], obtaining reliable labeled data is often difficult and may also raise privacy concerns.”
Research on Lightweight Road Defect Detection Algorithm Based on Multi-Scale Feature Fusion
Zhang, Q., Bao, J., Li, Y., & Gao, Y. (2025) · International Conference on Computer, Vision and Intelligent Technology (ICCVIT) · doi:10.1109/iccvit67848.2025.11391348
“Model transferability varied considerably by region, with mAP dropping 14.7% on Indian roads versus only 3.2% on Japanese roads when fine-tuned from a COCO pre-trained model [3] .”
Influential
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.