{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T17:27:13Z","timestamp":1773682033975,"version":"3.50.1"},"publisher-location":"Cham","reference-count":49,"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_15","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"245-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Unsupervised Domain Adaptation for\u00a0Monocular 3D Object Detection via\u00a0Self-training"],"prefix":"10.1007","author":[{"given":"Zhenyu","family":"Li","sequence":"first","affiliation":[]},{"given":"Zehui","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Liangji","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Qinhong","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"issue":"1","key":"15_CR1","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10994-009-5152-4","volume":"79","author":"S Ben-David","year":"2010","unstructured":"Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1), 151\u2013175 (2010)","journal-title":"Mach. Learn."},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3D-RPN: monocular 3D region proposal network for object detection. In: International Conference on Computer Vision (ICCV), pp. 9287\u20139296 (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Computer Vision and Pattern Recognition (CVPR), pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"15_CR4","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":"15_CR5","doi-asserted-by":"crossref","unstructured":"Carlucci, F.M., Porzi, L., Caputo, B., Ricci, E., Bulo, S.R.: Autodial: Automatic domain alignment layers. In: International Conference on Computer Vision (ICCV), pp. 5077\u20135085. IEEE (2017)","DOI":"10.1109\/ICCV.2017.542"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Yuan, Y., Zeng, G., Wang, J.: Semi-supervised semantic segmentation with cross pseudo supervision. In: Computer Vision and Pattern Recognition (CVPR), pp. 2613\u20132622 (2021)","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: Computer Vision and Pattern Recognition (CVPR), pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"15_CR8","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. In: Advances in Neural Information Processing Systems (NIPS) 28 (2015)"},{"key":"15_CR9","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: Computer Vision and Pattern Recognition (CVPR), pp. 3339\u20133348 (2018)","DOI":"10.1109\/CVPR.2018.00352"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: Graph-DETR3D: rethinking overlapping regions for multi-view 3D object detection. arXiv preprint arXiv:2204.11582 (2022)","DOI":"10.1145\/3503161.3547859"},{"key":"15_CR11","unstructured":"Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection. https:\/\/github.com\/open-mmlab\/mmdetection3d (2020)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Dubourvieux, F., Audigier, R., Loesch, A., Ainouz, S., Canu, S.: Unsupervised domain adaptation for person re-identification through source-guided pseudo-labeling. In: International Conference on Pattern Recognition (ICPR), pp. 4957\u20134964 (2021)","DOI":"10.1109\/ICPR48806.2021.9412964"},{"key":"15_CR13","unstructured":"Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning (ICML), pp. 1180\u20131189. PMLR (2015)"},{"issue":"1","key":"15_CR14","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. (JMLR) 17(1), 2030\u20132096 (2016)","journal-title":"J. Mach. Learn. Res. (JMLR)"},{"key":"15_CR15","unstructured":"Ge, Y., et al.: Self-paced contrastive learning with hybrid memory for domain adaptive object Re-ID. Adv. Neural Inf. Process. Syst. (NIPS) 33, 11309\u201311321 (2020)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: Computer Vision and Pattern Recognition (CVPR), pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"15_CR17","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (NIPS) 27 (2014)"},{"key":"15_CR18","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein GANs. In: Advances in Neural Information Processing Systems (NIPS) 30 (2017)"},{"key":"15_CR19","unstructured":"Hoffman, J., Wang, D., Yu, F., Darrell, T.: FCNs in the wild: pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649 (2016)"},{"key":"15_CR20","unstructured":"Kesten, R., et al.: Level 5 perception dataset 2020. https:\/\/level-5.global\/level5\/data\/ (2019)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Khodabandeh, M., Vahdat, A., Ranjbar, M., Macready, W.G.: A robust learning approach to domain adaptive object detection. In: International Conference on Computer Vision (ICCV), pp. 480\u2013490 (2019)","DOI":"10.1109\/ICCV.2019.00057"},{"key":"15_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"15_CR23","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2018.03.005","volume":"80","author":"Y Li","year":"2018","unstructured":"Li, Y., Wang, N., Shi, J., Hou, X., Liu, J.: Adaptive batch normalization for practical domain adaptation. Pattern Recogn. (PR) 80, 109\u2013117 (2018)","journal-title":"Pattern Recogn. (PR)"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: SimIPU: simple 2d image and 3D point cloud unsupervised pre-training for spatial-aware visual representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 1500\u20131508 (2022)","DOI":"10.1609\/aaai.v36i2.20040"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: Smoke: single-stage monocular 3D object detection via keypoint estimation. In: Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 996\u2013997 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"15_CR26","unstructured":"Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning (ICML), pp. 97\u2013105 (2015)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Unsupervised domain adaptive 3d detection with multi-level consistency. In: International Conference on Computer Vision (ICCV), pp. 8866\u20138875 (2021)","DOI":"10.1109\/ICCV48922.2021.00874"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Mancini, M., Porzi, L., Bulo, S.R., Caputo, B., Ricci, E.: Boosting domain adaptation by discovering latent domains. In: Computer Vision and Pattern Recognition (CVPR), pp. 3771\u20133780 (2018)","DOI":"10.1109\/CVPR.2018.00397"},{"key":"15_CR29","unstructured":"Mao, J., Shi, S., Wang, X., Li, H.: 3D object detection for autonomous driving: a review and new outlooks. arXiv preprint arXiv:2206.09474 (2022)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3D bounding box estimation using deep learning and geometry. In: Computer Vision and Pattern Recognition (CVPR), pp. 7074\u20137082 (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is pseudo-lidar needed for monocular 3d object detection? In: International Conference on Computer Vision (ICCV), pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: Computer Vision and Pattern Recognition (CVPR), pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"15_CR33","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3D object detection. arXiv preprint arXiv:1811.08188 (2018)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation. In: International Conference on Machine Learning (ICML), pp. 2988\u20132997. PMLR (2017)","DOI":"10.1109\/CVPR.2018.00392"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: Computer Vision and Pattern Recognition (CVPR), pp. 6956\u20136965 (2019)","DOI":"10.1109\/CVPR.2019.00712"},{"key":"15_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/978-3-319-49409-8_35","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"B Sun","year":"2016","unstructured":"Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443\u2013450. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_35"},{"key":"15_CR37","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in neural information processing systems (NIPS) 30 (2017)"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: International Conference on Computer Vision (ICCV), pp. 4068\u20134076 (2015)","DOI":"10.1109\/ICCV.2015.463"},{"key":"15_CR39","unstructured":"Wang, T., Xinge, Z., Pang, J., Lin, D.: Probabilistic and geometric depth: detecting objects in perspective. In: Conference on Robot Learning (CoRL), pp. 1475\u20131485 (2022)"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: Fcos3D: fully convolutional one-stage monocular 3d object detection. In: International Conference on Computer Vision Workshop (ICCVW), pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"15_CR41","unstructured":"Wang, X., Jin, Y., Long, M., Wang, J., Jordan, M.I.: Transferable normalization: towards improving transferability of deep neural networks. In: Advances in Neural Information Processing Systems (NIPS) 32 (2019)"},{"key":"15_CR42","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning (CoRL), pp. 180\u2013191 (2022)"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Weng, X., Kitani, K.: Monocular 3D object detection with pseudo-lidar point cloud. In: International Conference on Computer Vision Workshops (ICCVW) (2019)","DOI":"10.1109\/ICCVW.2019.00114"},{"key":"15_CR44","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Z.: Multi-level fusion based 3D object detection from monocular images. In: Computer Vision and Pattern Recognition (CVPR), pp. 2345\u20132353 (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: End-to-end semi-supervised object detection with soft teacher. In: International Conference on Computer Vision (ICCV), pp. 3060\u20133069 (2021)","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Yang, J., Shi, S., Wang, Z., Li, H., Qi, X.: ST3D++: denoised self-training for unsupervised domain adaptation on 3D object detection. arXiv preprint arXiv:2108.06682 (2021)","DOI":"10.1109\/CVPR46437.2021.01023"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Yang, J., Shi, S., Wang, Z., Li, H., Qi, X.: ST3D: self-training for unsupervised domain adaptation on 3D object detection. In: Computer Vision and Pattern Recognition (CVPR), pp. 10368\u201310378 (2021)","DOI":"10.1109\/CVPR46437.2021.01023"},{"key":"15_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, W., Li, W., Xu, D.: SRDAN: scale-aware and range-aware domain adaptation network for cross-dataset 3D object detection. In: Computer Vision and Pattern Recognition (CVPR), pp. 6769\u20136779 (2021)","DOI":"10.1109\/CVPR46437.2021.00670"},{"key":"15_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-030-01219-9_18","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Zou","year":"2018","unstructured":"Zou, Y., Yu, Z., Vijaya Kumar, B.V.K., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 297\u2013313. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_18"}],"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_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:08:51Z","timestamp":1667866131000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_15","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)"}}]}}