{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T16:26:19Z","timestamp":1783873579096,"version":"3.55.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734137","type":"print"},{"value":"9783031734144","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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\/978-3-031-73414-4_24","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:02:54Z","timestamp":1729789374000},"page":"417-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Distributionally Robust Loss for\u00a0Long-Tailed Multi-label Image Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7640-1281","authenticated-orcid":false,"given":"Dekun","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3358-5813","authenticated-orcid":false,"given":"Tailai","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7120-4209","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9546-5022","authenticated-orcid":false,"given":"Xinran","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5087-8178","authenticated-orcid":false,"given":"Xiaolin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9708-2000","authenticated-orcid":false,"given":"Zhe","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Aimar, E.S., Jonnarth, A., Felsberg, M., Kuhlmann, M.: Balanced product of calibrated experts for long-tailed recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 19967\u201319977 (2023)","DOI":"10.1109\/CVPR52729.2023.01912"},{"key":"24_CR2","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","volume":"106","author":"M Buda","year":"2018","unstructured":"Buda, M., Maki, A., Mazurowski, M.A.: A systematic study of the class imbalance problem in convolutional neural networks. Neural Netw. 106, 249\u2013259 (2018)","journal-title":"Neural Netw."},{"key":"24_CR3","unstructured":"Byrd, J., Lipton, Z.: What is the effect of importance weighting in deep learning? In: International Conference on Machine Learning, pp. 872\u2013881. PMLR (2019)"},{"key":"24_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":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chen, T., Xu, M., Hui, X., Wu, H., Lin, L.: Learning semantic-specific graph representation for multi-label image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 522\u2013531 (2019)","DOI":"10.1109\/ICCV.2019.00061"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177\u20135186 (2019)","DOI":"10.1109\/CVPR.2019.00532"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.Y., Song, Y., Belongie, S.: Class-balanced loss based on effective number of samples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9268\u20139277 (2019)","DOI":"10.1109\/CVPR.2019.00949"},{"key":"24_CR8","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"},{"issue":"1","key":"24_CR9","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., et al.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vision 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"24_CR10","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"24_CR11","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.patrec.2017.05.012","volume":"94","author":"H Guo","year":"2017","unstructured":"Guo, H., Fan, X., Wang, S.: Human attribute recognition by refining attention heat map. Pattern Recogn. Lett. 94, 38\u201345 (2017)","journal-title":"Pattern Recogn. Lett."},{"key":"24_CR12","doi-asserted-by":"publisher","unstructured":"Han, H., Wang, W.Y., Mao, B.H.: Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In: International Conference on Intelligent Computing, pp. 878\u2013887. Springer (2005). https:\/\/doi.org\/10.1007\/11538059_91","DOI":"10.1007\/11538059_91"},{"key":"24_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":"24_CR14","doi-asserted-by":"crossref","unstructured":"Huang, C., Li, Y., Loy, C.C., Tang, X.: Learning deep representation for imbalanced classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5375\u20135384 (2016)","DOI":"10.1109\/CVPR.2016.580"},{"key":"24_CR15","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, D., Han, B.: Cosmo: Content-style modulation for image retrieval with text feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 802\u2013812 (2021)","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, Y., Luo, J.: Improving pairwise ranking for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3617\u20133625 (2017)","DOI":"10.1109\/CVPR.2017.199"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Lin, D.: Probability guided loss for long-tailed multi-label image classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 1577\u20131585 (2023)","DOI":"10.1609\/aaai.v37i2.25244"},{"key":"24_CR19","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":"24_CR20","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: European conference on computer vision, pp. 740\u2013755. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Sun, W., Hong, Y., Teney, D., Gould, S.: Bi-directional training for composed image retrieval via text prompt learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5753\u20135762 (2024)","DOI":"10.1109\/WACV57701.2024.00565"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., Yu, S.X.: Large-scale long-tailed recognition in an open world. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2537\u20132546 (2019)","DOI":"10.1109\/CVPR.2019.00264"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Metwaly, K., Kim, A., Branson, E., Monga, V.: GlideNet: global, local and intrinsic based dense embedding network for multi-category attributes prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4835\u20134846 (2022)","DOI":"10.1109\/CVPR52688.2022.00479"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Neculai, A., Chen, Y., Akata, Z.: Probabilistic compositional embeddings for multimodal image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4547\u20134557 (2022)","DOI":"10.1109\/CVPRW56347.2022.00501"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., et\u00a0al.: PACO: parts and attributes of common objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7141\u20137151 (2023)","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"24_CR26","unstructured":"Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. In: International Conference on Machine Learning, pp. 4334\u20134343. PMLR (2018)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Ridnik, T., et al.: Asymmetric loss for multi-label classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 82\u201391 (2021)","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"24_CR28","doi-asserted-by":"publisher","unstructured":"Shen, L., Lin, Z., Huang, Q.: Relay backpropagation for effective learning of deep convolutional neural networks. In: European Conference on Computer Vision, pp. 467\u2013482. Springer (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_29","DOI":"10.1007\/978-3-319-46478-7_29"},{"key":"24_CR29","unstructured":"Su, J., Zhu, M., Murtadha, A., Pan, S., Wen, B., Liu, Y.: ZLPR: a novel loss for multi-label classification. arXiv preprint arXiv:2208.02955 (2022)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Sun, Y., Cheng, C., Zhang, Y., Zhang, C., Zheng, L., Wang, Z., Wei, Y.: Circle loss: a unified perspective of pair similarity optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6398\u20136407 (2020)","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: The iNaturalist species classification and detection dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8769\u20138778 (2018)","DOI":"10.1109\/CVPR.2018.00914"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: a unified framework for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2285\u20132294 (2016)","DOI":"10.1109\/CVPR.2016.251"},{"key":"24_CR33","unstructured":"Wang, Y.X., Ramanan, D., Hebert, M.: Learning to model the tail. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 7032\u20137042 (2017)"},{"key":"24_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, T., Li, G., Xu, R., Lin, L.: Multi-label image recognition by recurrently discovering attentional regions. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 464\u2013472 (2017)","DOI":"10.1109\/ICCV.2017.58"},{"key":"24_CR35","doi-asserted-by":"publisher","unstructured":"Wu, T., Huang, Q., Liu, Z., Wang, Y., Lin, D.: Distribution-balanced loss for multi-label classification in long-tailed datasets. In: European Conference on Computer Vision, pp. 162\u2013178. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_10","DOI":"10.1007\/978-3-030-58548-8_10"},{"key":"24_CR36","unstructured":"Yang, Y., Zha, K., Chen, Y., Wang, H., Katabi, D.: Delving into deep imbalanced regression. In: International Conference on Machine Learning, pp. 11842\u201311851. PMLR (2021)"},{"key":"24_CR37","doi-asserted-by":"publisher","unstructured":"Ye, J., He, J., Peng, X., Wu, W., Qiao, Y.: Attention-driven dynamic graph convolutional network for multi-label image recognition. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXI 16, pp. 649\u2013665. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_39","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: VideoLT: large-scale long-tailed video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7960\u20137969 (2021)","DOI":"10.1109\/ICCV48922.2021.00786"},{"key":"24_CR39","first-page":"34077","volume":"35","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Hooi, B., Hong, L., Feng, J.: Self-supervised aggregation of diverse experts for test-agnostic long-tailed recognition. Adv. Neural. Inf. Process. Syst. 35, 34077\u201334090 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Kang, B., Hooi, B., Yan, S., Feng, J.: Deep long-tailed learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3268118"}],"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\/978-3-031-73414-4_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:12:34Z","timestamp":1729789954000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73414-4_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031734137","9783031734144"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73414-4_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 October 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"}}]}}