{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:08:44Z","timestamp":1775002124779,"version":"3.50.1"},"reference-count":108,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Unsupervised domain adaptive object detection (UDA-OD) aims to deploy a detector trained on source domain(s) to a new, unlabeled target domain. Carrying out mean-teacher self-training for UDA-OD poses a significant challenge, given that its success depends heavily on the quality of pseudo boxes. While many earlier researches have mainly centered on cross-domain transferability, they often neglect the rich intra- and inter-domain semantic structures. As a result, this neglect empirically restricts the discriminative abilities of the learning model. In our study, we have found a notable alignment and synergy across contrastive learning, prototype learning, and mean-teacher self-training. Building on this insight, we introduce the\n                    <jats:italic>P<\/jats:italic>\n                    rototype-\n                    <jats:italic>o<\/jats:italic>\n                    riented\n                    <jats:italic>C<\/jats:italic>\n                    <jats:italic>o<\/jats:italic>\n                    ntrastive\n                    <jats:italic>M<\/jats:italic>\n                    ean\n                    <jats:italic>T<\/jats:italic>\n                    eacher (PoCoMT) for UDA-OD, a thorough and flexible framework that seamlessly integrates these three techniques to extract the most beneficial learning signals. Specifically, PoCoMT firstly generate more diverse and reliable probabilistic outputs from self-training through maximizing information entropy and maintaining semantic consistency; secondly, PoCoMT strives to reduce both intra-domain and inter-domain prototypical contrastive learning losses by elaborately designing a Prototype Alignment Network (ProtoAN) module, which fosters intra-domain feature aggregation, aligns inter-domain class structures, and reduces semantic loss between weak and strong augmentations of target domain data. Our ProtoAN can serve as a plugin module for traditional self-training frameworks to tackle the key problem of semantic loss in UDA-OD. Extensive experiments demonstrate that PoCoMT attains new state-of-the-art performance.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-44991-7","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:06:43Z","timestamp":1774598803000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prototype-oriented contrastive mean-teacher for unsupervised domain adaptive object detection"],"prefix":"10.1038","volume":"16","author":[{"given":"Qi","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwen","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufang","family":"Dan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Di","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"44991_CR1","unstructured":"Glenn, J. Ultralytics\/yolov5: v1.0 - Initial Release. (Zenodo, 2020)."},{"key":"44991_CR2","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)."},{"key":"44991_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, W., Sakaridis, C., Dai, D. & Van Gool, L. Domain adaptive faster r-cnn for object detection in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3339\u20133348 (2018).","DOI":"10.1109\/CVPR.2018.00352"},{"key":"44991_CR4","doi-asserted-by":"crossref","unstructured":"Zhu, X., Pang, J., Yang, C., Shi, J. & Lin, D. Adapting object detectors via selective cross-domain alignment. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 687\u2013696 (2019).","DOI":"10.1109\/CVPR.2019.00078"},{"key":"44991_CR5","doi-asserted-by":"crossref","unstructured":"Saito, K., Ushiku, Y., Harada, T. & Saenko, K. Strong-weak distribution alignment for adaptive object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 6956\u20136965 (2019).","DOI":"10.1109\/CVPR.2019.00712"},{"key":"44991_CR6","doi-asserted-by":"crossref","unstructured":"He, Z. & Zhang, L. Multi-adversarial faster-rcnn for unrestricted object detection. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 6668\u20136677 (2019).","DOI":"10.1109\/ICCV.2019.00677"},{"key":"44991_CR7","doi-asserted-by":"crossref","unstructured":"Xu, C.-D., Zhao, X.-R., Jin, X. & Wei, X.-S. Exploring categorical regularization for domain adaptive object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 11724\u201311733 (2020).","DOI":"10.1109\/CVPR42600.2020.01174"},{"key":"44991_CR8","doi-asserted-by":"crossref","unstructured":"Chen, C., Zheng, Z., Ding, X., Huang, Y. & Dou, Q. Harmonizing transferability and discriminability for adapting object detectors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8869\u20138878 (2020).","DOI":"10.1109\/CVPR42600.2020.00889"},{"key":"44991_CR9","doi-asserted-by":"crossref","unstructured":"Su, P. et al. Adapting object detectors with conditional domain normalization. In Proceedings of the European Conference on Computer Vision (ECCV). 403\u2013419 (Springer, 2020).","DOI":"10.1007\/978-3-030-58621-8_24"},{"key":"44991_CR10","doi-asserted-by":"publisher","unstructured":"Saito, K., Watanabe, K., Ushiku, Y. & Harada, T. Maximum classifier discrepancy for unsupervised domain adaptation. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3723\u20133732. https:\/\/doi.org\/10.1109\/CVPR.2018.00392 (2018).","DOI":"10.1109\/CVPR.2018.00392"},{"key":"44991_CR11","unstructured":"Yaroslav, G. et al. Domain-Adversarial Training of Neural Networks. arXiv:1505.07818 (2016)."},{"key":"44991_CR12","doi-asserted-by":"publisher","unstructured":"Eric, T., Hoffman, J., Saenko, K. & Darrell, T. Adversarial discriminative domain adaptation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2962\u20132971. https:\/\/doi.org\/10.1109\/CVPR.2017.316 (2017).","DOI":"10.1109\/CVPR.2017.316"},{"key":"44991_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Li, W., Chen, Y. & Duan, L. Unbiased mean teacher for cross-domain object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4091\u20134101 (2021).","DOI":"10.1109\/CVPR46437.2021.00408"},{"key":"44991_CR14","doi-asserted-by":"publisher","first-page":"1706","DOI":"10.1109\/TFUZZ.2023.3332751","volume":"32","author":"Z Wang","year":"2024","unstructured":"Wang, Z., Chen, L. & Wang, F.-Y. Fuzzy inference attention module for unsupervised domain adaptation. IEEE Trans. Fuzzy Syst. 32, 1706\u20131718. https:\/\/doi.org\/10.1109\/TFUZZ.2023.3332751 (2024).","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"44991_CR15","doi-asserted-by":"publisher","first-page":"111184","DOI":"10.1016\/j.patcog.2024.111184","volume":"160","author":"Z Wang","year":"2025","unstructured":"Wang, Z., Chen, L., He, J., Yang, L. & Wang, F.-Y. Exploring latent transferability of feature components. Pattern Recognit. 160, 111184. https:\/\/doi.org\/10.1016\/j.patcog.2024.111184 (2025).","journal-title":"Pattern Recognit."},{"key":"44991_CR16","doi-asserted-by":"crossref","unstructured":"Hao, Y., Forest, F. & Fink, O. Simplifying source-free domain adaptation for object detection: Effective self-training strategies and performance insights. In Computer Vision \u2013 ECCV 2024 (Leonardis, A. et al. eds.). 196\u2013213 (Springer Nature Switzerland, 2025).","DOI":"10.1007\/978-3-031-72949-2_12"},{"key":"44991_CR17","unstructured":"Tarvainen, A. & Valpola, H. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Adv. Neural Inf. Process. Syst. 30 (2017)."},{"key":"44991_CR18","doi-asserted-by":"crossref","unstructured":"Cai, Q. et al. Exploring object relation in mean teacher for cross-domain detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 11457\u201311466 (2019).","DOI":"10.1109\/CVPR.2019.01172"},{"key":"44991_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y.-J. et al. Cross-domain adaptive teacher for object detection. In CVPR (2022).","DOI":"10.1109\/CVPR52688.2022.00743"},{"key":"44991_CR20","unstructured":"Chen, M. et al. Learning domain adaptive object detection with probabilistic teacher. In ICML (2022)."},{"key":"44991_CR21","doi-asserted-by":"crossref","unstructured":"Zhu, J.-Y., Park, T., Isola, P. & Efros, A.\u00a0A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2223\u20132232 (2017).","DOI":"10.1109\/ICCV.2017.244"},{"key":"44991_CR22","doi-asserted-by":"publisher","first-page":"3746","DOI":"10.1002\/int.22434","volume":"36","author":"L Xiong","year":"2021","unstructured":"Xiong, L. et al. Source data-free domain adaptation of object detector through domain-specific perturbation. Int. J. Intell. Syst. 36, 3746\u20133766 (2021).","journal-title":"Int. J. Intell. Syst."},{"key":"44991_CR23","first-page":"452","volume":"37","author":"Q Chu","year":"2023","unstructured":"Chu, Q., Li, S., Chen, G., Li, K. & Li, X. Adversarial alignment for source free object detection. Proc. AAAI Conf. Artif. Intell. 37, 452\u2013460 (2023).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"44991_CR24","doi-asserted-by":"crossref","unstructured":"Deng, J., Li, W. & Duan, L. Balanced teacher for source-free object detection. In IEEE Transactions on Circuits and Systems for Video Technology (2024).","DOI":"10.1109\/TCSVT.2024.3376380"},{"key":"44991_CR25","doi-asserted-by":"crossref","unstructured":"VS, V., Oza, P. & Patel, V.\u00a0M. Instance relation graph guided source-free domain adaptive object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3520\u20133530 (2023).","DOI":"10.1109\/CVPR52729.2023.00343"},{"key":"44991_CR26","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, Z. & Zhang, Y. Exploiting low-confidence pseudo-labels for source-free object detection. In Proceedings of the 31st ACM International Conference on Multimedia. 5370\u20135379 (2023).","DOI":"10.1145\/3581783.3612273"},{"key":"44991_CR27","doi-asserted-by":"publisher","first-page":"26797","DOI":"10.1007\/s10489-023-04950-5","volume":"53","author":"JH Park","year":"2023","unstructured":"Park, J. H. et al. Adversarial representation teaching with perturbation-agnostic student-teacher structure for semi-supervised learning. Appl. Intell. 53, 26797\u201326809. https:\/\/doi.org\/10.1007\/s10489-023-04950-5 (2023).","journal-title":"Appl. Intell."},{"key":"44991_CR28","doi-asserted-by":"publisher","unstructured":"Ngo, B.\u00a0H., Jeong Chae, Y., Kwon, J.\u00a0E., Hyeon Park, J. & Cho, S.\u00a0I. Improved knowledge transfer for semi-supervised domain adaptation via trico training strategy. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 19157\u201319166. (2023).https:\/\/doi.org\/10.1109\/ICCV51070.2023.01760.","DOI":"10.1109\/ICCV51070.2023.01760"},{"key":"44991_CR29","doi-asserted-by":"publisher","unstructured":"Wang, Z. et al. Teacher-student instance-level adversarial augmentation for single domain generalized medical image segmentation. In IEEE Transactions on Medical Imaging. 1\u20131. (2025). https:\/\/doi.org\/10.1109\/TMI.2025.3605162.","DOI":"10.1109\/TMI.2025.3605162"},{"key":"44991_CR30","doi-asserted-by":"publisher","unstructured":"Wang, Z., Chen, L., Tian, Y., He, J. & Philip Chen, C.\u00a0L. Spatially enhanced refined classifier for cross-scene hyperspectral image classification. In IEEE Transactions on Geoscience and Remote Sensing. Vol. 63. 1\u201315. (2025). https:\/\/doi.org\/10.1109\/TGRS.2024.3524631.","DOI":"10.1109\/TGRS.2024.3524631"},{"key":"44991_CR31","doi-asserted-by":"crossref","unstructured":"Cao, S., Joshi, D., Gui, L.-Y. & Wang, Y.-X. Contrastive mean teacher for domain adaptive object detectors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 23839\u201323848 (2023).","DOI":"10.1109\/CVPR52729.2023.02283"},{"key":"44991_CR32","unstructured":"Minghao, X., Hang, W., Bingbing, N., Qi, T. & Wenjun, Z. Cross-domain detection via graph-induced prototype alignment. In CVPR. 12355\u201312364 (2020)."},{"key":"44991_CR33","doi-asserted-by":"publisher","first-page":"166488","DOI":"10.1109\/ACCESS.2021.3136567","volume":"9","author":"BH Ngo","year":"2021","unstructured":"Ngo, B. H., Kim, J. H., Chae, Y. J. & Cho, S. I. Multi-view collaborative learning for semi-supervised domain adaptation. IEEE Access 9, 166488\u2013166501. https:\/\/doi.org\/10.1109\/ACCESS.2021.3136567 (2021).","journal-title":"IEEE Access"},{"key":"44991_CR34","unstructured":"Jiuzheng, Y. et al. Rethinking weak-to-strong augmentation in source-free domain adaptive object detection. arXiv preprint arXiv:2410.05557 (2024)."},{"key":"44991_CR35","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P. et al. Supervised contrastive learning. Adv. Neural Inf. Process. Syst. 33, 18661\u201318673 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"44991_CR36","doi-asserted-by":"crossref","unstructured":"Yuan, X., Cheng, G., Yan, K., Zeng, Q. & Han, J. Small object detection via coarse-to-fine proposal generation and imitation learning. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 6317\u20136327 (2023).","DOI":"10.1109\/ICCV51070.2023.00581"},{"key":"44991_CR37","doi-asserted-by":"publisher","first-page":"7509","DOI":"10.1109\/TPAMI.2022.3216454","volume":"45","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Chen, J., Zhang, J. & Shan, H. Learning representation for clustering via prototype scattering and positive sampling. IEEE Trans. Pattern Anal. Mach. Intell. 45, 7509\u20137524. https:\/\/doi.org\/10.1109\/TPAMI.2022.3216454 (2023).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44991_CR38","doi-asserted-by":"publisher","unstructured":"Belal, A., Meethal, A., Romero, F.\u00a0P., Pedersoli, M. & Granger, E. Multi-source domain adaptation for object detection with prototype-based mean teacher. In 2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). 1266\u20131275 (2024). https:\/\/doi.org\/10.1109\/WACV57701.2024.00131.","DOI":"10.1109\/WACV57701.2024.00131"},{"key":"44991_CR39","unstructured":"Ting, C., Simon, K., Mohammad, N. & Geoffrey, H. A simple framework for contrastive learning of visual representations. arXiv:2002.05709 (2020)."},{"key":"44991_CR40","unstructured":"Dai, J., Li, Y., He, K. & Sun, J. R-fcn: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems (NIPS). 379\u2013387 (2016)."},{"key":"44991_CR41","doi-asserted-by":"crossref","unstructured":"Dai, J. et al. Deformable convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 764\u2013773 (2017).","DOI":"10.1109\/ICCV.2017.89"},{"key":"44991_CR42","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J. & Wei, Y. Relation networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3588\u20133597 (2018).","DOI":"10.1109\/CVPR.2018.00378"},{"key":"44991_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2117\u20132125 (2017).","DOI":"10.1109\/CVPR.2017.106"},{"key":"44991_CR44","doi-asserted-by":"crossref","unstructured":"Peng, C. et al. Megdet: A large mini-batch object detector. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 6181\u20136189 (2018).","DOI":"10.1109\/CVPR.2018.00647"},{"key":"44991_CR45","doi-asserted-by":"crossref","unstructured":"Singh, B., Li, H., Sharma, A. & Davis, L.\u00a0S. R-fcn-3000 at 30fps: Decoupling detection and classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1081\u20131090 (2018).","DOI":"10.1109\/CVPR.2018.00119"},{"key":"44991_CR46","doi-asserted-by":"crossref","unstructured":"Hsu, C.-C., Tsai, Y.-H., Lin, Y.-Y. & Yang, M.-H. Every pixel matters: Center-aware feature alignment for domain adaptive object detector. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IX 16. 733\u2013748 (Springer, 2020).","DOI":"10.1007\/978-3-030-58545-7_42"},{"key":"44991_CR47","doi-asserted-by":"crossref","unstructured":"Sindagi, V.\u00a0A., Oza, P., Yasarla, R. & Patel, V.\u00a0M. Prior-based domain adaptive object detection for hazy and rainy conditions. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16. 763\u2013780 (Springer, 2020).","DOI":"10.1007\/978-3-030-58568-6_45"},{"key":"44991_CR48","doi-asserted-by":"crossref","unstructured":"Vs, V., Gupta, V., Oza, P., Sindagi, V.\u00a0A. & Patel, V.\u00a0M. Mega-CDA: Memory guided attention for category-aware unsupervised domain adaptive object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4516\u20134526 (2021).","DOI":"10.1109\/CVPR46437.2021.00449"},{"key":"44991_CR49","doi-asserted-by":"crossref","unstructured":"Inoue, N., Furuta, R., Yamasaki, T. & Aizawa, K. Cross-domain weakly-supervised object detection through progressive domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5001\u20135009 (2018).","DOI":"10.1109\/CVPR.2018.00525"},{"key":"44991_CR50","doi-asserted-by":"crossref","unstructured":"RoyChowdhury, A. et al. Automatic adaptation of object detectors to new domains using self-training. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 780\u2013790 (2019).","DOI":"10.1109\/CVPR.2019.00087"},{"key":"44991_CR51","doi-asserted-by":"crossref","unstructured":"Khodabandeh, M., Vahdat, A., Ranjbar, M. & Macready, W.\u00a0G. A robust learning approach to domain adaptive object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 480\u2013490 (2019).","DOI":"10.1109\/ICCV.2019.00057"},{"key":"44991_CR52","unstructured":"Hsu, H.-K. et al. Progressive domain adaptation for object detection. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 749\u2013757 (2020)."},{"key":"44991_CR53","unstructured":"Rodriguez, A.\u00a0L. & Mikolajczyk, K. Domain adaptation for object detection via style consistency. arXiv preprint arXiv:1911.10033 (2019)."},{"key":"44991_CR54","doi-asserted-by":"crossref","unstructured":"Kim, T., Jeong, M., Kim, S., Choi, S. & Kim, C. Diversify and match: A domain adaptive representation learning paradigm for object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12456\u201312465 (2019).","DOI":"10.1109\/CVPR.2019.01274"},{"key":"44991_CR55","unstructured":"Sohn, K. et al. A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020)."},{"key":"44991_CR56","doi-asserted-by":"publisher","unstructured":"Oza, P., Sindagi, V.\u00a0A., VS, V. & Patel, V.\u00a0M. Unsupervised domain adaptation of object detectors: A survey. In IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 46. 4018\u20134040 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2022.3217046.","DOI":"10.1109\/TPAMI.2022.3217046"},{"key":"44991_CR57","unstructured":"Hadsell, R., Chopra, S. & LeCun, Y. Dimensionality reduction by learning an invariant mapping. In CVPR (2006)."},{"key":"44991_CR58","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S. & Girshick, R. Momentum contrast for unsupervised visual representation learning. In CVPR (2020).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"44991_CR59","unstructured":"Grill, J.-B. et al. Bootstrap your own latent: A new approach to self-supervised learning. In NeurIPS (2020)."},{"key":"44991_CR60","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M. et al. Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural Inf. Process. Syst. 33, 9912\u20139924 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"44991_CR61","unstructured":"Tomasev, N. et al. Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet? In ICML Workshop (2022)."},{"key":"44991_CR62","doi-asserted-by":"crossref","unstructured":"Van Gansbeke, W., Vandenhende, S., Georgoulis, S. & Van Gool, L. Unsupervised semantic segmentation by contrasting object mask proposals. In ICCV (2021).","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"44991_CR63","doi-asserted-by":"crossref","unstructured":"H\u00e9naff, O.\u00a0J. et al. Efficient visual pretraining with contrastive detection. In ICCV (2021).","DOI":"10.1109\/ICCV48922.2021.00993"},{"key":"44991_CR64","unstructured":"Wei, F., Gao, Y., Wu, Z., Hu, H. & Lin, S. Aligning pretraining for detection via object-level contrastive learning. In NeurIPS (2021)."},{"key":"44991_CR65","doi-asserted-by":"crossref","unstructured":"Bai, Y., Chen, X., Kirillov, A., Yuille, A. & Berg, A.\u00a0C. Point-level region contrast for object detection pre-training. In CVPR (2022).","DOI":"10.1109\/CVPR52688.2022.01559"},{"key":"44991_CR66","doi-asserted-by":"crossref","unstructured":"Yao, L. et al. G-DetKD: Towards general distillation framework for object detectors via contrastive and semantic-guided feature imitation. In ICCV (2021).","DOI":"10.1109\/ICCV48922.2021.00357"},{"key":"44991_CR67","doi-asserted-by":"crossref","unstructured":"VS, V., Oza, P. & Patel, V.\u00a0M. Towards online domain adaptive object detection. In WACV (2023).","DOI":"10.1109\/WACV56688.2023.00055"},{"key":"44991_CR68","unstructured":"Tanwisuth, K. et al. A prototype-oriented framework for unsupervised domain adaptation. In Neural Information Processing Systems (2021)."},{"key":"44991_CR69","doi-asserted-by":"publisher","unstructured":"Pan, Y. et al. Transferrable prototypical networks for unsupervised domain adaptation. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2234\u20132242. https:\/\/doi.org\/10.1109\/CVPR.2019.00234 (2019).","DOI":"10.1109\/CVPR.2019.00234"},{"key":"44991_CR70","unstructured":"Snell, J., Swersky, K. & Zemel, R. Prototypical networks for few-shot learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917. 4080\u20134090 (Curran Associates Inc., 2017)."},{"key":"44991_CR71","doi-asserted-by":"publisher","unstructured":"Tian, L. et al. Prototypes-oriented transductive few-shot learning with conditional transport. In 2023 IEEE\/CVF International Conference on Computer Vision (ICCV). 16271\u201316280. https:\/\/doi.org\/10.1109\/ICCV51070.2023.01495 (2023).","DOI":"10.1109\/ICCV51070.2023.01495"},{"key":"44991_CR72","unstructured":"Junnan, L., Pan, Z., Caiming, X., Richard, S. & Steven, C. H.\u00a0H. Prototypical contrastive learning of unsupervised representations. arXiv abs\/2005.04966 (2020)."},{"key":"44991_CR73","unstructured":"K.\u00a0J., J., Salman, K., Fahad, S.\u00a0K. & Vineeth, N.\u00a0B. Towards open world object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021) (2021)."},{"key":"44991_CR74","doi-asserted-by":"publisher","unstructured":"Li, A., Yuan, P. & Li, Z. Semi-supervised object detection via multi-instance alignment with global class prototypes. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00958 (2022).","DOI":"10.1109\/CVPR52688.2022.00958"},{"key":"44991_CR75","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Wang, Z. & Mao, Y. Rpn prototype alignment for domain adaptive object detector. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01224 (2021).","DOI":"10.1109\/CVPR46437.2021.01224"},{"key":"44991_CR76","unstructured":"Aming, W., Yahong, H., Linchao, Z., Yi, Y. & Cheng, D. Universal-prototype augmentation for few-shot object detection. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)."},{"key":"44991_CR77","unstructured":"Gomes, R., Krause, A. & Perona, P. Discriminative clustering by regularized information maximization. In International Conference on Neural Information Processing Systems (NIPS\u201910). Vol. 1. 775\u2013783 (Curran Associates Inc., 2010)."},{"key":"44991_CR78","unstructured":"Ganin, Y. & Lempitsky, V. Unsupervised domain adaptation by backpropagation. In Proceedings of the International Conference on Machine Learning (ICML). 1180\u20131189 (PMLR, 2015)."},{"key":"44991_CR79","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Huang, D., Liu, S. & Wang, Y. Cross-domain object detection through coarse-to-fine feature adaptation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 13766\u201313775 (2020).","DOI":"10.1109\/CVPR42600.2020.01378"},{"key":"44991_CR80","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P. & Girshick, R. Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2961\u20132969 (2017).","DOI":"10.1109\/ICCV.2017.322"},{"key":"44991_CR81","doi-asserted-by":"publisher","first-page":"109974","DOI":"10.1016\/j.patcog.2023.109974","volume":"145","author":"Z Lihua","year":"2024","unstructured":"Lihua, Z., Nianxin, L., Mao, Y., Xiatian, Z. & Song, T. Source-free domain adaptation with class prototype discovery. Pattern Recognit. 145, 109974. https:\/\/doi.org\/10.1016\/j.patcog.2023.109974 (2024).","journal-title":"Pattern Recognit."},{"key":"44991_CR82","unstructured":"Liu, Y.-C. et al. Unbiased teacher for semi-supervised object detection. In Proceedings of the International Conference on Learning Representations (ICLR) (2021)."},{"key":"44991_CR83","doi-asserted-by":"crossref","unstructured":"Sch\u00f6lkopf, B., Platt, J. & Hofmann, T. Analysis of representations for domain adaptation. In Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference. 137\u2013144 (2007).","DOI":"10.7551\/mitpress\/7503.001.0001"},{"key":"44991_CR84","doi-asserted-by":"crossref","unstructured":"Cordts, M. et al. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3213\u20133223 (2016).","DOI":"10.1109\/CVPR.2016.350"},{"key":"44991_CR85","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1007\/s11263-018-1072-8","volume":"126","author":"C Sakaridis","year":"2018","unstructured":"Sakaridis, C., Dai, D. & Van Gool, L. Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vis. 126, 973\u2013992 (2018).","journal-title":"Int. J. Comput. Vis."},{"key":"44991_CR86","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J. & Zisserman, A. The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010).","journal-title":"Int. J. Comput. Vis."},{"key":"44991_CR87","doi-asserted-by":"crossref","unstructured":"Li, S., Ye, M., Zhu, X., Zhou, L. & Xiong, L. Source-free object detection by learning to overlook domain style. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8014\u20138023 (2022).","DOI":"10.1109\/CVPR52688.2022.00785"},{"key":"44991_CR88","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C. & Urtasun, R. Vision meets robotics: The Kitti dataset. Int. J. Robot. Res. 32, 1231\u20131237 (2013).","journal-title":"Int. J. Robot. Res."},{"key":"44991_CR89","doi-asserted-by":"crossref","unstructured":"Johnson-Roberson, M. et al. Driving in the matrix: Can virtual worlds replace human-generated annotations for real world tasks? 746\u2013753 (2017).","DOI":"10.1109\/ICRA.2017.7989092"},{"key":"44991_CR90","doi-asserted-by":"publisher","unstructured":"Yu, F. et al. Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2633\u20132642. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00271 (2020).","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"44991_CR91","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"44991_CR92","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O. et al. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"44991_CR93","unstructured":"Yuxin, W., Alexander, K., Francisco, M., Wan-Yen, L. & Ross, G. Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)."},{"key":"44991_CR94","unstructured":"DeVries, T. & Taylor, G.\u00a0W. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)."},{"key":"44991_CR95","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S. & Yang, Y. Random erasing data augmentation. In AAAI (2020).","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"44991_CR96","doi-asserted-by":"publisher","unstructured":"Ramamonjison, R., Banitalebi-Dehkordi, A., Kang, X., Bai, X. & Zhang, Y. Simrod: A simple adaptation method for robust object detection. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 3550\u20133559. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00355 (2021).","DOI":"10.1109\/ICCV48922.2021.00355"},{"key":"44991_CR97","doi-asserted-by":"crossref","unstructured":"Zhao, L. & Wang, L. Task-specific inconsistency alignment for domain adaptive object detection. In CVPR (2022).","DOI":"10.1109\/CVPR52688.2022.01382"},{"key":"44991_CR98","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, X. & Yuan, Y. Semantic-complete graph matching for domain adaptive object detection. In CVPR (SIGMA, 2022).","DOI":"10.1109\/CVPR52688.2022.00522"},{"key":"44991_CR99","unstructured":"Shen, Z., Maheshwari, H., Yao, W. & Savvides, M. Scl: Towards accurate domain adaptive object detection via gradient detach based stacked complementary losses. arXiv preprint arXiv:1911.02559 (2019)."},{"key":"44991_CR100","doi-asserted-by":"crossref","unstructured":"Li, C. et al. Spatial attention pyramid network for unsupervised domain adaptation. In Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIII 16. 481\u2013497 (Springer, 2020).","DOI":"10.1007\/978-3-030-58601-0_29"},{"key":"44991_CR101","first-page":"4178","volume":"44","author":"A Wu","year":"2021","unstructured":"Wu, A., Han, Y., Zhu, L. & Yang, Y. Instance-invariant domain adaptive object detection via progressive disentanglement. IEEE Trans. Pattern Anal. Mach. Intell. 44, 4178\u20134193 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44991_CR102","unstructured":"Xingxu, Y., Sicheng, Z., Pengfei, X. & Jufeng, Y. Multi-source domain adaptation for object detection. arXiv:2106.15793 (2021)."},{"key":"44991_CR103","first-page":"8474","volume":"35","author":"X Li","year":"2021","unstructured":"Li, X. et al. A free lunch for unsupervised domain adaptive object detection without source data. Proc. AAAI Conf. Artif. Intell. 35, 8474\u20138481 (2021).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"44991_CR104","doi-asserted-by":"crossref","unstructured":"Liu, Q., Lin, L., Shen, Z. & Yang, Z. Periodically exchange teacher-student for source-free object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 6414\u20136424 (2023).","DOI":"10.1109\/ICCV51070.2023.00590"},{"key":"44991_CR105","doi-asserted-by":"publisher","unstructured":"Nath Kundu, J., Venkat, N., Rahul, M.\u00a0V. & Venkatesh Babu, R. Universal source-free domain adaptation. In 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 4543\u20134552. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00460 (2020).","DOI":"10.1109\/CVPR42600.2020.00460"},{"key":"44991_CR106","doi-asserted-by":"publisher","first-page":"10646","DOI":"10.1109\/TPAMI.2025.3593669","volume":"47","author":"S Qu","year":"2025","unstructured":"Qu, S. et al. Glc++: Source-free universal domain adaptation through global-local clustering and contrastive affinity learning. IEEE Trans. Pattern Anal. Mach. Intell. 47, 10646\u201310663. https:\/\/doi.org\/10.1109\/TPAMI.2025.3593669 (2025).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44991_CR107","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.1109\/TIP.2024.3361691","volume":"33","author":"X Liu","year":"2024","unstructured":"Liu, X., Huang, Y., Wang, H., Xiao, Z. & Zhang, S. Universal and scalable weakly-supervised domain adaptation. IEEE Trans. Image Process. 33, 1313\u20131325. https:\/\/doi.org\/10.1109\/TIP.2024.3361691 (2024).","journal-title":"IEEE Trans. Image Process."},{"key":"44991_CR108","doi-asserted-by":"publisher","first-page":"7548","DOI":"10.1109\/TNNLS.2022.3214930","volume":"35","author":"Z Qin","year":"2024","unstructured":"Qin, Z., Yang, L., Gao, F., Hu, Q. & Shen, C. Uncertainty-aware aggregation for federated open set domain adaptation. IEEE Trans. Neural Netw. Learn. Syst. 35, 7548\u20137562. https:\/\/doi.org\/10.1109\/TNNLS.2022.3214930 (2024).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44991-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44991-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44991-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T23:12:12Z","timestamp":1774998732000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-44991-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":108,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["44991"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-44991-7","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]},"assertion":[{"value":"21 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"10869"}}