{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:42:22Z","timestamp":1778085742772,"version":"3.51.4"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","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\/978-3-031-20074-8_40","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"698-714","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Long-tail Detection with\u00a0Effective Class-Margins"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3654-7505","authenticated-orcid":false,"given":"Jang","family":"Hyun Cho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9846-4369","authenticated-orcid":false,"given":"Philipp","family":"Kr\u00e4henb\u00fchl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"40_CR1","unstructured":"Bartlett, P., Foster, D.J., Telgarsky, M.: Spectrally-normalized margin bounds for neural networks. arXiv preprint arXiv:1706.08498 (2017)"},{"key":"40_CR2","unstructured":"Bartlett, P.L., Mendelson, S.: Rademacher and gaussian complexities: risk bounds and structural results. J. Mach. Learn. Res. 3, 463\u2013482 (2003)"},{"key":"40_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"40_CR4","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N., Ma, T.: Learning imbalanced datasets with label-distribution-aware margin loss. arXiv preprint arXiv:1906.07413 (2019)"},{"key":"40_CR5","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":"40_CR6","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"40_CR7","doi-asserted-by":"crossref","unstructured":"Chen, K., Lin, W., Li, J., See, J., Wang, J., Zou, J.: AP-loss for accurate one-stage object detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3782\u20133798 (2020)","DOI":"10.1109\/TPAMI.2020.2991457"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., Girshick, R., Doll\u00e1r, P., Berg, A.C., Kirillov, A.: Boundary IoU: improving object-centric image segmentation evaluation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15334\u201315342 (2021)","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"40_CR9","unstructured":"Dave, A., Doll\u00e1r, P., Ramanan, D., Kirillov, A., Girshick, R.: Evaluating large-vocabulary object detectors: the devil is in the details. arXiv preprint arXiv:2102.01066 (2021)"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"40_CR11","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Huang, W.: Exploring classification equilibrium in long-tailed object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00340"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., et al.: Simple copy-paste is a strong data augmentation method for instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2918\u20132928 (2021)","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"40_CR14","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"40_CR16","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":"40_CR17","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":"40_CR18","unstructured":"Kakade, S.M., Sridharan, K., Tewari, A.: On the complexity of linear prediction: risk bounds, margin bounds, and regularization. In: Proceedings of the 21st International Conference on Neural Information Processing Systems, NIPS\u201908, Curran Associates Inc., Red Hook, NY, USA, pp. 793\u2013800 (2008)"},{"key":"40_CR19","unstructured":"Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=r1gRTCVFvB"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Koltchinskii, V., Panchenko, D.: Empirical margin distributions and bounding the generalization error of combined classifiers. Ann. Stat. 30(1), 1\u201350 (2002)","DOI":"10.1214\/aos\/1015362183"},{"key":"40_CR21","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et al.: The open images dataset v4. Int. J. Comput. Vision 128(7), 1956\u20131981 (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"40_CR22","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21002\u201321012 (2020)"},{"key":"40_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10991\u201311000 (2020)","DOI":"10.1109\/CVPR42600.2020.01100"},{"key":"40_CR24","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":"40_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"40_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"40_CR27","unstructured":"Liu, W., Wen, Y., Yu, Z., Yang, M.: Large-margin softmax loss for convolutional neural networks. In: International Conference on Machin Learning, vol. 2, p. 7 (2016)"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"40_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/978-3-030-01234-2_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"K Oksuz","year":"2018","unstructured":"Oksuz, K., Cam, B.C., Akbas, E., Kalkan, S.: Localization recall precision (LRP): a new performance metric for object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 521\u2013537. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_31"},{"key":"40_CR30","unstructured":"Oksuz, K., Cam, B.C., Akbas, E., Kalkan, S.: A ranking-based, balanced loss function unifying classification and localisation in object detection. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"40_CR31","doi-asserted-by":"crossref","unstructured":"Oksuz, K., Cam, B.C., Akbas, E., Kalkan, S.: Rank & sort loss for object detection and instance segmentation. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00300"},{"key":"40_CR32","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":"40_CR33","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: YOLO9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"40_CR34","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"40_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28, pp. 91\u201399 (2015)"},{"key":"40_CR36","doi-asserted-by":"crossref","unstructured":"Rolinek, M., Musil, V., Paulus, A., Vlastelica, M., Michaelis, C., Martius, G.: Optimizing rank-based metrics with blackbox differentiation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00764"},{"key":"40_CR37","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"40_CR38","doi-asserted-by":"crossref","unstructured":"Tan, J., Lu, X., Zhang, G., Yin, C., Li, Q.: Equalization loss v2: a new gradient balance approach for long-tailed object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1685\u20131694 (2021)","DOI":"10.1109\/CVPR46437.2021.00173"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Tan, J., et al.: Equalization loss for long-tailed object recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11662\u201311671 (2020)","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"40_CR40","unstructured":"Tang, K., Huang, J., Zhang, H.: Long-tailed classification by keeping the good and removing the bad momentum causal effect. In: Conference on Neural Information Processing Systems (2020)"},{"key":"40_CR41","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":"40_CR42","doi-asserted-by":"crossref","unstructured":"Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin softmax for face verification. IEEE Signal Process. Lett. 25(7), 926\u2013930 (2018)","DOI":"10.1109\/LSP.2018.2822810"},{"key":"40_CR43","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, et al.: Seesaw loss for long-tailed instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9695\u20139704 (2021)","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Wang, T., et al.: The devil is in classification: a simple framework for long-tail instance segmentation. arXiv preprint arXiv:2007.11978 (2020)","DOI":"10.1007\/978-3-030-58568-6_43"},{"key":"40_CR45","doi-asserted-by":"crossref","unstructured":"Wu, J., Song, L., Wang, T., Zhang, Q., Yuan, J.: Forest R-CNN: large-vocabulary long-tailed object detection and instance segmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1570\u20131578 (2020)","DOI":"10.1145\/3394171.3413970"},{"key":"40_CR46","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"40_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: MosaicOS: a simple and effective use of object-centric images for long-tailed object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 417\u2013427 (2021)","DOI":"10.1109\/ICCV48922.2021.00047"},{"key":"40_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: VarifocalNet: an IoU-aware dense object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"40_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S.Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"40_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, S., Li, Z., Yan, S., He, X., Sun, J.: Distribution alignment: a unified framework for long-tail visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2361\u20132370 (2021)","DOI":"10.1109\/CVPR46437.2021.00239"},{"key":"40_CR51","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Probabilistic two-stage detection. arXiv preprint arXiv:2103.07461 (2021)"},{"key":"40_CR52","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Simple multi-dataset detection. In: arXiv preprint arXiv:2102.13086 (2021)"},{"key":"40_CR53","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"}],"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\/978-3-031-20074-8_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:34:00Z","timestamp":1668198840000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_40","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":"12 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)"}}]}}