{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:08Z","timestamp":1775229788293,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732010","type":"print"},{"value":"9783031732027","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73202-7_6","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:17:37Z","timestamp":1732112257000},"page":"93-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Bucketed Ranking-Based Losses for\u00a0Efficient Training of\u00a0Object Detectors"],"prefix":"10.1007","author":[{"given":"Feyza","family":"Yavuz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baris Can","family":"Cam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6802-6405","authenticated-orcid":false,"given":"Adnan Harun","family":"Dogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0066-1517","authenticated-orcid":false,"given":"Kemal","family":"Oksuz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3760-6722","authenticated-orcid":false,"given":"Emre","family":"Akbas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0915-5917","authenticated-orcid":false,"given":"Sinan","family":"Kalkan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"6_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-030-58545-7_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Brown","year":"2020","unstructured":"Brown, A., Xie, W., Kalogeiton, V., Zisserman, A.: Smooth-AP: smoothing the path towards large-scale image retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 677\u2013694. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_39"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade R-CNN: delving into high quality object detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Hybrid task cascade for instance segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00511"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Chen, K., et al.: Towards accurate one-stage object detection with AP-loss. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00526"},{"key":"6_CR6","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. (TPAMI) 1 (2020)","DOI":"10.1109\/CVPR.2019.00526"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Dai, Z., Cai, B., Lin, Y., Chen, J.: Unsupervised pre-training for detection transformers. IEEE Trans. Pattern Anal. Mach. Intell. 1\u201311 (2022). https:\/\/doi.org\/10.1109\/tpami.2022.3216514, http:\/\/dx.doi.org\/10.1109\/TPAMI.2022.3216514","DOI":"10.1109\/tpami.2022.3216514"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Jia, D., et al.: DETRs with hybrid matching (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"6_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-3-030-58595-2_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"K Kim","year":"2020","unstructured":"Kim, K., Lee, H.S.: Probabilistic anchor assignment with IoU prediction for object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 355\u2013371. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_22"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Law, H., Deng, J.: CornerNet: detecting objects as paired keypoints. In: The European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: accelerate DETR training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: accelerate DETR training by introducing query denoising (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"issue":"2","key":"6_CR17","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"TY Lin","year":"2020","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 42(2), 318\u2013327 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"6_CR18","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":"6_CR19","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., et al.: 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":"6_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6_CR21","unstructured":"Mohapatra, P., Jawahar, C., Kumar, M.P.: Efficient optimization for average precision SVM. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Mohapatra, P., Rol\u00ednek, M., Jawahar, C., Kolmogorov, V., Pawan\u00a0Kumar, M.: Efficient optimization for rank-based loss functions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00389"},{"key":"6_CR23","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":"6_CR24","doi-asserted-by":"crossref","unstructured":"Oksuz, K., Cam, B.C., Akbas, E., Kalkan, S.: Rank & sort loss for object detection and instance segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3009\u20133018 (2021)","DOI":"10.1109\/ICCV48922.2021.00300"},{"key":"6_CR25","unstructured":"Oksuz, K., Cam, B.C., Kahraman, F., Baltaci, Z.S., Kalkan, S., Akbas, E.: Mask-aware IoU for anchor assignment in real-time instance segmentation. In: The British Machine Vision Conference (BMVC) (2021)"},{"issue":"10","key":"6_CR26","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TPAMI.2020.2981890","volume":"43","author":"K Oksuz","year":"2020","unstructured":"Oksuz, K., Cam, B.C., Kalkan, S., Akbas, E.: Imbalance problems in object detection: a review. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3388\u20133415 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., Lin, D.: Libra R-CNN: towards balanced learning for object detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00091"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Qian, Q., Chen, L., Li, H., Jin, R.: DR loss: improving object detection by distributional ranking. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01218"},{"issue":"6","key":"6_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65\u2013386 (1958)","DOI":"10.1037\/h0042519"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Gupta, A., Girshick, R.: Training region-based object detectors with online hard example mining. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.89"},{"key":"6_CR33","unstructured":"Sun, P., et al.: SparseR-CNN: end-to-end object detection with learnable proposals. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)"},{"key":"6_CR34","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"6_CR35","unstructured":"Zhang, X., Wan, F., Liu, C., Ji, R., Ye, Q.: FreeAnchor: learning to match anchors for visual object detection. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Rongguang, Y., Dongwei, R.: Distance-IoU loss: faster and better learning for bounding box regression. In: AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"6_CR37","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. ArXiv abs\/2010.04159 (2020). https:\/\/api.semanticscholar.org\/CorpusID:222208633"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: DETRs with collaborative hybrid assignments training (2022)","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73202-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:05:51Z","timestamp":1732115151000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}