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 101–200 of 369
Kapil, R., Marvasti-Zadeh, S. M., Erbilgin, N., & Ray, N. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00808 · Cited by 11
“The goal of UDA is to transfer knowledge from a source domain (e.g., RGB) to a target domain (e.g., thermal) without relying on annotations specific to the target domain [40].”
BackgroundXu, R., Samat, A., Zhu, E., Li, E., & Li, W. (2024) · Remote Sensing · doi:10.3390/rs16111974 · Cited by 10
Unsupervised Domain Adaptation for Multi-Stain Cell Detection in Breast Cancer with Transformers
Pina, O., & Vilaplana, V. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00513 · Cited by 8
“The approach applies adversarial learning at different levels to exploit the multi-scale nature inherent in object detection tasks [12].”
BackgroundLearning domain-adaptive palmprint anti-spoofing feature from multi-source domains
Liu, C., Shao, H., & Zhong, D. (2024) · Displays · doi:10.1016/j.displa.2024.102871 · Cited by 10
Li, W., Shang, S., Shang, R., Feng, D., Zhang, W., Wang, C., Feng, J., & Xu, S. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3523712 · Cited by 12
“To improve the performance of FSL, some researchers have adopted domain adaptation methods to optimize the process [26].”
Qu, S., Chen, G., Zhang, J., Li, Z., He, W., & Tao, D. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-024-02335-w · Cited by 8
Cascade-UDA: A Cascade paradigm for unsupervised domain adaptation
Zhan, M., Wu, Z., Xu, H., Zhu, X., & Hu, R. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129924 · Cited by 10
Zhao, J., Li, Y., Zhou, Y. Z., Du, W.-L., Li, X., Yao, R., & Saddik, A. E. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3553094 · Cited by 8
“Unsupervised domain adaptation (UDA) methods for RS images are proposed as a solution to tackle this problem, aiming to bridge the knowledge gap by transferring learning from a labeled source domain to unseen and unlabeled target domains [4].”
Jiang, Z., Zhang, Y., Wang, Z., Yu, Y. K., Zhang, Z., Zhang, M., Zhang, L., & Cheng, B. (2024) · Remote Sensing · doi:10.3390/rs16020304 · Cited by 10
Continuous unsupervised domain adaptation using stabilized representations and experience replay
Rostami, M. G. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128017 · Cited by 10
Spatiotemporal Ego-Graph Domain Adaptation for Traffic Prediction With Data Missing
Xu, C., Wang, Q., Zhang, W., & Sun, C. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3447549 · Cited by 8
“From the theoretical perspective, Domain Adaptation [26] provides support for the neural networks achieving out-of-distribution generalization and cross-domain knowledge transfer.”
Imbalanced few-shot bearing fault diagnosis via hybrid enhanced VAE-WGAN and attention-guided WDCNN
Xie, Y., Zhang, L., Liu, H., & Hu, C. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adf98d · Cited by 7
Li, J., Zhang, X., Li, L., Wang, X., Cheng, J., Gao, C., & Ling, J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108905 · Cited by 9
Oriented Clustering Reppoints for Resident Space Objects Detection in Time Delay Integration Images
Fu, Z., Lei, Y., Tang, X., Xu, T., Tian, G., Gao, S., Du, J., & Yang, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3498319 · Cited by 8
“With the rapid development of deep learning, detectors based on neural networks occupy an absolutely dominant position in the object detection [37].”
Scale-Consistent and Temporally Ensembled Unsupervised Domain Adaptation for Object Detection
Guo, L., Zhang, Y., Liu, J., Liu, H., & Li, Y. (2025) · Sensors · doi:10.3390/s25010230 · Cited by 7
“To address this challenge, unsupervised domain adaptation for object detection (UDA-OD) techniques leverage unlabeled target domain data to reduce the domain shift and improve detection performance [3].”
Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation
Vanhele, B., Zoomers, B., Put, J., Reeth, F. V., & Michiels, N. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00986-9_4 · Cited by 8
Assessing domain gap for continual domain adaptation in object detection
Doan, A.-D., Nguyen, B. L., Gupta, S., Reid, I. D., Wagner, M., & Chin, T.-J. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103885 · Cited by 8
Zeroth- and first-order difference discrimination for unsupervised domain adaptation
Wang, J., Chen, X., & Zhang, X.-L. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-01283-1 · Cited by 7
Real-time object detection method with single-domain generalization based on YOLOv8
Zhou, Y., & Qian, H. (2024) · Journal of Real-Time Image Processing · doi:10.1007/s11554-024-01572-z · Cited by 7
“In pursuit of enhancing model generalizability, researchers have introduced a plethora of domain adaptation techniques, encompassing feature re-mapping, adversarial training, and adaptive network architectures [25].”
DJAN: Deep Joint Adaptation Network for Wildlife Image Recognition
Zhang, C., & Zhang, J. (2023) · Animals · doi:10.3390/ani13213333 · Cited by 7
Few-shot Fine-tuning is All You Need for Source-free Domain AdaptationPreprint
Lee, S., Seo, S., Kim, J., Lee, Y., & Hwang, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.00792 · Cited by 11
“image classification [13, 47, 54, 25], semantic segmentation [52, 35, 56], object detection [34, 50], and person reidentification [31, 4].”
BackgroundA survey on domain adaptive object detection
Tingting, Z., & Youjun, W. (2025) · The Computer Journal · doi:10.1093/comjnl/bxaf120 · Cited by 7
Zhang, X., Wei, F., Wang, Y., Zhao, W., Li, F., & Chu, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00055 · Cited by 6
“Domain adaptation has gained widespread attention in recent years [4, 22, 31, 34, 39, 41, 42, 50].”
Quality over quantity: a data-centric survey of annotation errors in object detection datasets
Hussain, A., Ullah, K., Afaq, M., Munsif, M., Hussain, A., & Baik, S. W. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11502-z · Cited by 9
“Oza et al. (2023) provided a comprehensive review of the recent methods and challenges of unsupervised adoption of Object detectors.”
Joshi, A., Amrita, A., Mathur, R. S., Kumar, N., & Tripathi, P. (2024) · Wiley eBooks · doi:10.1002/9781394200733.ch9 · Cited by 6
Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning
Hong, Z., Shen, L., & Liu, T. (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/cvpr52733.2024.02721 · Cited by 13
“Target-specified NTL. Target-specified NTL aims to restrict the generalization of a deep learning model toward a certain target domain, which can be seen as an anti-task to domain adaptation (DA) [14, 22, 33, 41, 44].”
BackgroundContinual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks
Cui, S., Li, Y., Li, J., Tang, X., Su, B., Xu, F., & Xiong, H. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02363-0 · Cited by 10
“SIDD has wide-ranging applications in high-level vision tasks, including object detection (Lin et al. 2024; Oza et al. 2023), image classification (Wang et al. 2017), text recognition (Shi et al. 2016), and autonomous driving (Wang et al. 2023c).”
Tan, L., Peng, Z., Song, Y., Liu, X., Jiang, H., Liu, S., Wu, W., & Xiang, Z. (2025) · Entropy · doi:10.3390/e27040426 · Cited by 6
Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditions
Zhang, X., & Chou, C.-H. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00507 · Cited by 6
“Due to the prohibitive cost of labeling target domain data, unsupervised domain adaptation (UDA) is sometimes required to facilitate effective fine-tuning on the target domain without any labels [27].”
Domain adaptive detection framework for multi-center bone tumor detection on radiographs
Li, B., Xu, D., Lin, H., Wu, R., Wu, S., Shao, J., Zhang, J., Dai, H., Wei, D., Huang, B., et al. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102522 · Cited by 6
Development and Adaptation of Robotic Vision in the Real World: The Challenge of Door Detection
Antonazzi, M., Luperto, M., Borghese, N. A., & Basilico, N. (2025) · Journal of Field Robotics · doi:10.1002/rob.70084 · Cited by 8
“However, other (more recent) models of the same families of object detectors can be used instead.”
An Intelligent Financial Fraud Detection Model Using Knowledge Graph-Integrated Deep Neural Network
Zhu, W., & Chen, Z. (2024) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126624502670 · Cited by 6
Wang, Z., Liu, Y., & Zhang, E. (2024) · Aerospace · doi:10.3390/aerospace11110948 · Cited by 5
Minimizing Human Labeling in Training Deep Models for Pedestrian Intention Prediction
Riaz, M. N., Wielgosz, M., & López, A. M. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3565667 · Cited by 5
“In this context, UDA proposals have mainly focused on visual tasks involving isolated images, such as object detection [31], semantic segmentation [41], monocular depth estimation [19], and animal pose estimation [27].”
Yang, K., Hu, Z., Zhao, X., Wang, Q., Hu, D., & Zhai, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111129 · Cited by 5
Machine learning based multi-parameter droplet optimisation model study
Li, T., Lu, L., Zeng, Q., & Liao, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-09435-8 · Cited by 5
“Image segmentation is one of the key image processing techniques in computer vision 23,24 .”
Domain adaptive underwater object detection via complementary style-aware learning
Gao, X., Yang, M., & Xie, Z. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108174 · Cited by 5
Mitigating Negative Transfer via Reducing Environmental Disagreement
Sun, H., Xie, Z., He, H., & Li, M. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3672777 · Cited by 5
Toward Real-Time Earth System Intelligence Through Advancements in Onboard AI Processing: A review
Barretta, D., Marini, L., Razzano, F., Guerrisi, G., Sandberg, S., Prete, R. D., Zancan, V., Mariotti, E., Furano, G., Manovi, L., et al. (2026) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2026.3665978 · Cited by 8
“The so-called domain gap problem [307], [308] is a significant problem for AI applications in general.”
A Text-Specific Domain Adaptive Network for Scene Text Detection in the Wild
He, X., Yuan, J., Li, M., Wang, R., Wang, H., & Li, Z. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04873-1 · Cited by 5
Moment matching of joint distributions for unsupervised domain adaptation
Zhang, B., Zhang, X., Zhou, Z., Li, Y., Li, Y., & Huang, F. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103944 · Cited by 5
Transferable Deployment of Semantic Edge Inference Systems via Unsupervised Domain Adaption
Jiao, W., Bi, S., Li, X., Guo, C., Chen, H., & Quan, Z. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3564304 · Cited by 5
“Depending on the availability of labeled data samples in the target domain, few-shot learning [27], [28] and domain adaptation [29], [30], [31], [32] are two common transfer learning methodologies.”
Adversarially Trained Object Detector for Unsupervised Domain Adaptation
Fujii, K., Kera, H., & Kawamoto, K. (2022) · IEEE Access · doi:10.1109/access.2022.3180344 · Cited by 9
“Many domain adaptation approaches have also been proposed for object detection (Oza et al. 2021).”
InfluentialProgressive Domain-style Translation for Nighttime Tracking
Zhang, J., Li, Z., Wei, R., & Wang, Y. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612305 · Cited by 7
“It is widely explored in classification [47], detection [31], and segmentation [8].”
BackgroundCodamal: Contrastive Domain Adaptation for Malaria Detection in Low-Cost Microscopes
Dave, I. R., de Blegiers, T., Chen, C., & Shah, M. A. (2024) · Proceedings - International Conference on Image Processing · doi:10.1109/icip51287.2024.10647834 · Cited by 5
Cross-Task Crash Severity Analysis With Cost-Sensitive Transfer Graph Convolutional Network
Wan, J., & Zhu, S. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3550862 · Cited by 4
“In recent years, unsupervised transfer learning [56], e.g., unsupervised deep domain adaptation [43], [44], generative adversarial networks based transfer learning [45], [46], has also attracted much attention of researchers.”
Mobgazenet: robust gaze estimation mobile network based on progressive attention mechanisms
Abdelrahman, A. A., Hempel, T., Khalifa, A., Strazdas, D., & Al-Hamadi, A. K. (2025) · Machine Vision and Applications · doi:10.1007/s00138-025-01690-z · Cited by 5
“Attention mechanisms have proven valuable in various computer vision tasks, such as image classification [39, 69] and segmentation [42, 68, 71].”
Lan, B., Stramigioli, S., & Niu, K. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3575202 · Cited by 5
“This is common in deep learning [33], [34] to adapt the data from an old distribution to a new distribution: Firstly, the model was pre-trained using 100% five people’s dataset, then continually trained using the rest participant’s 80% dataset and evaluate on the same person’s 20% dataset.”
Prompt-affinity multi-modal class centroids for unsupervised domain adaption
Deng, X., Wang, Y., Xie, Y., Li, X., Tang, M., Fang, M., & Zhang, W. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112095 · Cited by 4
Shah, S. F. A., Khan, M. Q., Alsuwaylimi, A. A., & Alenezi, L. A. (2026) · IEEE Access · doi:10.1109/access.2026.3669588 · Cited by 4
Improving Mental Health Support in Engineering Education using Machine Learning and Eye-Tracking
Liu, Y., Lu, W., Zavareh, A. T., Rigsby, M., & Zoghi, B. (2023) · IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie58773.2023.10343428 · Cited by 4
TiROD: Tiny Robotics Dataset and Benchmark for Continual Object Detection
Pasti, F., Monte, R. D., Pezze, D. D., Susto, G. A., & Bellotto, N. (2026) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-026-02430-9 · Cited by 4
LRNTRM-YOLO: Research on Real-Time Recognition of Non-Tobacco-Related Materials
Zhang, C., Yun, L., Yang, C., Chen, Z., & Cheng, F. (2025) · Agronomy · doi:10.3390/agronomy15020489 · Cited by 4
AdaShift: Anti-Collapse and Real-Time Deep Model Evolution for Mobile Vision Applications
Ma, K., Guo, B., Liu, S., Fang, C., Luo, S., Zheng, Z., & Yu, Z. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3572215 · Cited by 4
“Many established studies have focused on addressing the accuracy degradation problem caused by distribution shifts [3], with domain adaptation being a prominent approach [7].”
Semantic Dual-Adversarial Network for Blended-Target Domain Adaptation
Lu, Y., Hu, X. L., Huang, H., Lai, Z., & Li, X. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613144 · Cited by 4
“Recently, remarkable progress in deep learning has been achieved in many applications [1], [2], [3], [4], [5].”
Zhou, Y., Gong, J., Lu, W.-J., Gu, N., Chong, K., & Wang, Z. (2022) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus55513.2022.9987190 · Cited by 4
Assessing systematic weaknesses of DNNs using counterfactuals
Gannamaneni, S. S., Möck, M., & Akila, M. (2024) · AI and Ethics · doi:10.1007/s43681-023-00407-0 · Cited by 5
“…et al. 2019), de-fending against adversarial attacks (Akhtar and Mian 2018; Chakraborty et al. 2018), and improving domain generalization (Oza et al. 2021; Wang and Deng 2018), only recently, a few works have focused on identifying systematic weaknesses of DNNs (d’Eon et al. 2022;…”
BackgroundDA-BEV: Unsupervised Domain Adaptation for Bird’s Eye View Perception
Jiang, K., Huang, J., Xie, W., Lei, J., Li, Y., Shao, L., & Lu, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73007-8_19 · Cited by 11
“It has been extensively explored for various 2D computer vision tasks [16, 46, 80, 84] that perceive environments in a 2D space.”
BackgroundAntonazzi, M., Luperto, M., Borghese, N. A., & Basilico, N. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802847 · Cited by 5
“Standard domain adaptation techniques [2], [3], where fine–tuning and feature alignment are exploited to train models that can withstand the shift to a target domain, face scalability issues in such a scenario.”
FMDL: Enhancing Open-World Object Detection with foundation models and dynamic learning
Huang, Y., Hu, J., & Luo, R. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127050 · Cited by 4
OSSA: Unsupervised One-Shot Style Adaptation
Gerster, R., Caesar, H., Rapp, M., Wolpert, A., & Teutsch, M. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-91672-4_9 · Cited by 3
Hierarchical Meta Alignment for cross-domain object detection
Li, Y., Zhang, S., Liu, Y., & Yang, J. J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111247 · Cited by 3
Lin, B., Nie, D., Wu, X., Shen, X., & Cheng-hu, Y. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108203 · Cited by 4
SALLM: Open world object detection empowered by self adaptive learning and large model
Huang, Y., Ye, L., & Luo, R. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129375 · Cited by 3
Knowledge-guided distribution alignment for cross-domain few-shot learning
Chen, J., Xu, F., Lyu, X., Zeng, T., Li, X., & Chen, S. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114316 · Cited by 4
Li, J., Qu, Z., & Yin, X. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3613972 · Cited by 3
“Currently, UDA techniques are widely used in image classification [5], [6], [7], image segmentation [8], [9], [10] and object detection [11], [12], [13].”
TITAN: Query-Token Based Domain Adaptive Adversarial Learning
Ashraf, T., & Bashir, J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00031 · Cited by 3
“However, there are relatively fewer works specifically addressing SF-DAOD [13, 40, 62, 71, 88].”
Chiou, C.-Y., Chen, W., Huang, C.-R., Fann, Y. C., Latour, L. L., & Chung, P. (2025) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2025.3624582 · Cited by 3
“The domain shift problem will degrade the performance of deep learning-based models [13], [14], [15].”
Tian, H., Mi, J., Tong, S., & Li, Y. (2025) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2025.111810 · Cited by 3
Martinez-Esteso, J. P., Castellanos, F. J., & Gallego, A. J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130864 · Cited by 3
Multi-source domain adaptation with knowledge transfer for credit risk classification
Li, Y., & Shao, X. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113656 · Cited by 3
Wang, K., Zhu, Q., Zhao, J., Zheng, C., Shao, W., & Zhang, D. (2026) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2025.3647679 · Cited by 4
“Therefore,cross-subjectalignment methodscanimprovethemodel’sperformanceondatafrom multiplecenters[26],whichincludesintroducingadversarial training,domainalignment,orsamplere-labelingduringthe feature extraction stage.”
Reliable-Teacher: Uncertainty-Guided Collaborative Learning for Nighttime Object Detection
Luo, H., Xi, Y., Jia, W., Xiao, J., Ren, J., Yuan, D., Miao, Q., & He, X. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3665871 · Cited by 3
“To address the high cost of labor-intensive annotations, researchers have attempted to perform Unsupervised Domain Adaptive Object Detection (UDA-OD) [6], aiming to generalize detectors trained on a labeled source domain to an unlabeled target domain.”
Tang, R., Li, Z., Jin, X., Lin, Y., Zeng, J., Xu, M., Dong, H., Lan, W., & Pan, L. (2026) · LWT · doi:10.1016/j.lwt.2026.119192 · Cited by 3
Domain-Adaptive Benthonic Organism Detection via Uniformizing Light Field and Color Distribution
Chen, T., & Wang, N. (2026) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2026.3667579 · Cited by 4
“To overcome the domain shifting challenge, tremendous approaches have been proposed, and can be roughly divided into three categories, i.e., domain-invariant feature learning, pseudo-label learning, and style conversion [24].”
Deep Learning-Based Gaze Estimation: A Review
Abdelrahman, A. A., Al-Tawil, B., & Al-Hamadi, A. (2026) · Robotics · doi:10.3390/robotics15040069 · Cited by 3
Self-labeling in multivariate causality and quantification for adaptive machine learning
Ren, Y., Yen, A. H., & Li, G. P. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112595 · Cited by 3
Gao, D., Wang, Q., Yang, J., & Wu, J. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105404 · Cited by 3
Improving generalization capability of object detectors via efficient global attention
Chen, J., & Er, M. J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130287 · Cited by 3
Xu, D., Wang, B., Zhu, D., Zheng, C., Wu, H., Wang, R., Sun, J., Xie, M., Li, X., Wu, L., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02158-0 · Cited by 3
“12 , Oza et al. 13 , Gu et al. 14 .”
From Handheld to Unconstrained Object Detection: a Weakly-supervised On-line Learning Approach
Maiettini, E., Maracani, A., Camoriano, R., Pasquale, G., Tikhanoff, V., Rosasco, L., & Natale, L. (2022) · IEEE RO-MAN · doi:10.1109/ro-man53752.2022.9900780 · Cited by 4
“Another related field in Computer Vision is Unsupervised Domain adaptation for object detection [35].”
BackgroundCross-pollination of knowledge for object detection in domain adaptation for industrial automation
Rehman, A. U., & Gallo, I. (2024) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-024-00372-9 · Cited by 4
“…majority of the recent OD-based UDA methods, including the production of accurate pseudo labels (Yu et al. 2022; Zhao et al. 2020; VS et al. 2023; Oza et al. 2023) and the adoption of data augmentation techniques (Mekhalfi et al. 2023; Hendrycks et al. 2019, 2021; Michaelis et al. 2019), have…”
Achieving the Safety and Security of the End-to-End AV Pipeline
Curran, N. T., Cho, M., Feng, R., Liu, L., Tang, B., MohajerAnsari, P., Domeke, A., Pesé, M. D., & Shin, K. G. (2023) · doi:10.1145/3689936.3694694 · Cited by 3
Embracing Domain Gradient Conflicts: Domain Generalization Using Domain Gradient Equilibrium
Zhang, Z., Li, Y., & Shin, B. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681141 · Cited by 4
“Many existing works attempt to tackle this problem via un-supervised domain adaptation (UDA) [19, 29, 36, 39] or multiple domain generalization (MDG) [4, 15, 55].”
Tao, L., Qian, J., Gong, C., Zhang, D., & Luo, Y. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3502470 · Cited by 3
Domain adaptation with temporal ensembling to local attention region search for object detection
Shi, H., He, Z., & Hwang, K. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112846 · Cited by 3
Multi-Modal MR Image Segmentation Strategy for Brain Tumors Based on Domain Adaptation
Yang, Q., Jing, R., & Mu, J. (2024) · Computers · doi:10.3390/computers13120347 · Cited by 3
Multi-Granularity Domain-Adaptive Teacher for Unsupervised Remote Sensing Object Detection
Fang, F., Kang, J.-N., Li, S., Tian, P., Liu, Y., Luo, C., & Zhou, S. (2025) · Remote Sensing · doi:10.3390/rs17101743 · Cited by 5
Improving Object Detection via Local-global Contrastive LearningPreprint
Triantafyllidou, D., Parisot, S., Leonardis, A., & McDonagh, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.05058 · Cited by 5
“Such failures to ensure content preservation may in turn adversely affect performance in downstream object detection tasks [41], where this effect is exemplified in Fig.”
A second-order knowledge filter transfer learning algorithm for modeling nonlinear systems
Han, H., Li, M., Wu, X., Yang, H., & Qiao, J. (2025) · Science China Technological Sciences · doi:10.1007/s11431-024-2857-7 · Cited by 2
Mo, R., Lin, W., Zhong, H., Xu, M., & Li, K. (2025) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2025.3575790 · Cited by 3
“It promotes the model’s accuracy in predicting unseen data of the target domain and has exhibited remarkable achievements in classification tasks, including natural language processing [34], [35] and object detection [36].”
FAST: Foreground-aware active self-training for domain adaptive object detection
Zhang, D., Deng, H., Wang, H., Du, Z., Liu, G., Li, J., & Ye, M. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.108201 · Cited by 3
Qin, H., Lu, X. B., Wei, Z., & Chen, N. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754959 · Cited by 3
Deep learning methods for image recognition and classification in smart environmental systems
Rishi, N., Kumar, A., & Kumari, R. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-34254-7.00004-0 · Cited by 3
VOS-net: real-time oil spill detection in uav videos via lightweight adapter tuning
Liu, Z., Sun, C., Gao, L., Jing, Y., Chen, Y., Ma, A., & Zhong, Y. (2025) · International Journal of Digital Earth · doi:10.1080/17538947.2025.2586907 · Cited by 2
Domain Adaptive Representation Learning for Attack Detection in Smart Grids
Miao, K., Zhang, M., Fan, B., & Guan, X. (2025) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2025.3642949 · Cited by 2
“Despite the promising perspectives, a core challenge in DA is minimizing distribution discrepancy across domains while decreasing the lower bound of the target error [16], i.e., searching for a feature space where the distributions of source and target samples can be well aligned.”
Double-boundary awareness of shared categories for source-free universal domain adaptation
Wang, Z., Guo, J., Sun, X., Luo, Y., & Chen, A. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131473 · Cited by 4
Adaptive Noise-Resilient Test-Time Adaptation for RF Signal Recognition
Zha, H., Wang, H., Zhang, Z., Zhan, H., Gui, G., & Lin, Y. (2026) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2026.3657107 · Cited by 2
“Although methods such as Domain Adaptation (DA) and Domain Generalization (DG) are widely studied [21], [22], [23], their reliance on labeled source data and offline retraining hinders their deployment on privacy-sensitive and energy-constrained edge devices.”
Kariri, A., & Elleithy, K. M. (2026) · Electronics · doi:10.3390/electronics15050979 · Cited by 2
Unsupervised Domain Adaptive Thermal Infrared Tracking
Liu, Q., Li, Q., Li, X., Pi, J., Yuan, D., & Liu, Y. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668654 · Cited by 5
“[10] is usually used to solve the problem of domain shift, and it has been widely studied in image classification [11], [12], object detection [13], [14], and semantic segmentation [15], [16].”
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.