{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T06:56:32Z","timestamp":1780556192854,"version":"3.54.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20077-9_37","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"629-645","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["MTTrans: Cross-domain Object Detection with\u00a0Mean Teacher Transformer"],"prefix":"10.1007","author":[{"given":"Jinze","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yohei","family":"Nakata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Denis","family":"Gudovskiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomoyuki","family":"Okuno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kurt","family":"Keutzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanghang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"37_CR1","first-page":"26831","volume":"34","author":"Y Bai","year":"2021","unstructured":"Bai, Y., Mei, J., Yuille, A.L., Xie, C.: Are transformers more robust than cnns? Adv. Neural Inf. Process. Syst. 34, 26831\u201326843 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"37_CR2","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, pp. 11457\u201311466 (2019)","DOI":"10.1109\/CVPR.2019.01172"},{"key":"37_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"37_CR4","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, pp. 3339\u20133348 (2018)","DOI":"10.1109\/CVPR.2018.00352"},{"key":"37_CR5","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509 (2019)"},{"key":"37_CR6","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, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"37_CR8","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, pp. 4091\u20134101 (2021)","DOI":"10.1109\/CVPR46437.2021.00408"},{"key":"37_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"1","key":"37_CR10","first-page":"2030","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030\u20132096 (2016)","journal-title":"J. Mach. Learn. Res."},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Guo, Q., Qiu, X., Liu, P., Shao, Y., Xue, X., Zhang, Z.: Star-transformer. arXiv preprint arXiv:1902.09113 (2019)","DOI":"10.18653\/v1\/N19-1133"},{"key":"37_CR12","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, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"37_CR13","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1007\/978-3-030-58545-7_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C-C Hsu","year":"2020","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: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 733\u2013748. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_42"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Johnson-Roberson, M., Barto, C., Mehta, R., Sridhar, S.N., Rosaen, K., Vasudevan, R.: Driving in the matrix: can virtual worlds replace human-generated annotations for real world tasks? arXiv preprint arXiv:1610.01983 (2016)","DOI":"10.1109\/ICRA.2017.7989092"},{"key":"37_CR16","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, pp. 12456\u201312465 (2019)","DOI":"10.1109\/CVPR.2019.01274"},{"key":"37_CR17","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"37_CR18","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9404\u20139413 (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"37_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Unsupervised domain adaptive 3D detection with multi-level consistency. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8866\u20138875 (2021)","DOI":"10.1109\/ICCV48922.2021.00874"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"37_CR24","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":"37_CR25","doi-asserted-by":"crossref","unstructured":"Rezaeianaran, F., Shetty, R., Aljundi, R., Reino, D.O., Zhang, S., Schiele, B.: Seeking similarities over differences: similarity-based domain alignment for adaptive object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9204\u20139213 (2021)","DOI":"10.1109\/ICCV48922.2021.00907"},{"key":"37_CR26","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, pp. 6956\u20136965 (2019)","DOI":"10.1109\/CVPR.2019.00712"},{"issue":"9","key":"37_CR27","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. Vision 126(9), 973\u2013992 (2018)","journal-title":"Int. J. Comput. Vision"},{"key":"37_CR28","first-page":"596","volume":"33","author":"K Sohn","year":"2020","unstructured":"Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. Adv. Neural Inf. Process. Syst. 33, 596\u2013608 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"37_CR29","unstructured":"Sohn, K., Zhang, Z., Li, C.L., Zhang, H., Lee, C.Y., Pfister, T.: A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020)"},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Sun, Q., et al.: Sugar: subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism. In: Proceedings of the Web Conference 2021, pp. 2081\u20132091 (2021)","DOI":"10.1145\/3442381.3449822"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"37_CR32","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Exploring sequence feature alignment for domain adaptive detection transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1730\u20131738 (2021)","DOI":"10.1145\/3474085.3475317"},{"key":"37_CR34","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11724\u201311733 (2020)","DOI":"10.1109\/CVPR42600.2020.01174"},{"key":"37_CR35","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3060\u20133069 (2021)","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Xu, M., Wang, H., Ni, B., Tian, Q., Zhang, W.: Cross-domain detection via graph-induced prototype alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12355\u201312364 (2020)","DOI":"10.1109\/CVPR42600.2020.01237"},{"key":"37_CR37","unstructured":"Xu, T., Chen, W., Wang, P., Wang, F., Li, H., Jin, R.: Cdtrans: cross-domain transformer for unsupervised domain adaptation. arXiv preprint arXiv:2109.06165 (2021)"},{"key":"37_CR38","unstructured":"Yang, J., Liu, J., Xu, N., Huang, J.: Tvt: transferable vision transformer for unsupervised domain adaptation. arXiv preprint arXiv:2108.05988 (2021)"},{"key":"37_CR39","doi-asserted-by":"crossref","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: Reppoints: point set representation for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9657\u20139666 (2019)","DOI":"10.1109\/ICCV.2019.00975"},{"key":"37_CR40","unstructured":"Yu, F., et al.: Bdd100k: a diverse driving video database with scalable annotation tooling, vol. 2, no. 5, p. 6. arXiv preprint arXiv:1805.04687 (2018)"},{"key":"37_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Delving deep into the generalization of vision transformers under distribution shifts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7277\u20137286 (2022)","DOI":"10.1109\/CVPR52688.2022.00713"},{"key":"37_CR42","unstructured":"Zhang, J., Huang, J., Luo, Z., Zhang, G., Lu, S.: Da-detr: domain adaptive detection transformer by hybrid attention. arXiv preprint arXiv:2103.17084 (2021)"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Zheng, L., Shen, L., Tian, L., Wang, S., Wang, J., Tian, Q.: Scalable person re-identification: a benchmark. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1116\u20131124 (2015)","DOI":"10.1109\/ICCV.2015.133"},{"key":"37_CR44","doi-asserted-by":"crossref","unstructured":"Zhong, C., Wang, J., Feng, C., Zhang, Y., Sun, J., Yokota, Y.: Pica: point-wise instance and centroid alignment based few-shot domain adaptive object detection with loose annotations. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2329\u20132338 (2022)","DOI":"10.1109\/WACV51458.2022.00047"},{"key":"37_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 11106\u201311115 (2021)","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"37_CR46","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, pp. 687\u2013696 (2019)","DOI":"10.1109\/CVPR.2019.00078"},{"key":"37_CR47","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20077-9_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:20:49Z","timestamp":1667866849000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"6 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}