{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T17:11:05Z","timestamp":1778433065550,"version":"3.51.4"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T00:00:00Z","timestamp":1636416000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T00:00:00Z","timestamp":1636416000000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s11263-021-01533-0","type":"journal-article","created":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T09:02:31Z","timestamp":1636448551000},"page":"95-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Distribution-Aware Margin Calibration for Semantic Segmentation in Images"],"prefix":"10.1007","volume":"130","author":[{"given":"Litao","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongsheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7240-3541","authenticated-orcid":false,"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,9]]},"reference":[{"key":"1533_CR1","doi-asserted-by":"crossref","unstructured":"Abraham, N., & Khan, N. M. (2019). A novel focal tversky loss function with improved attention u-net for lesion segmentation. In: ISBI pp. 683\u2013687.","DOI":"10.1109\/ISBI.2019.8759329"},{"key":"1533_CR2","doi-asserted-by":"crossref","unstructured":"Ahmed, F., Tarlow, D., & Batra, D. (2015). Optimizing expected intersection-over-union with candidate-constrained crfs. In: ICCV, pp. 1850\u20131858.","DOI":"10.1109\/ICCV.2015.215"},{"key":"1533_CR3","unstructured":"Allan, M., Shvets, A., Kurmann, T., Zhang, Z., Duggal, R., Su, Y.H., Rieke, N., Laina, I., Kalavakonda, N., Bodenstedt, S., et\u00a0al. (2017). robotic instrument segmentation challenge. CoRR"},{"key":"1533_CR4","doi-asserted-by":"crossref","unstructured":"Berman, M., Rannen\u00a0Triki, A., Blaschko, M.B. (2018). The lov\u00e1sz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: CVPR, pp. 4413\u20134421.","DOI":"10.1109\/CVPR.2018.00464"},{"key":"1533_CR5","doi-asserted-by":"crossref","unstructured":"Blaschko, M. B., & Lampert, C. H. (2008). Learning to localize objects with structured output regression. In: ECCV, pp. 2\u201315.","DOI":"10.1007\/978-3-540-88682-2_2"},{"key":"1533_CR6","doi-asserted-by":"crossref","unstructured":"Boser, B.E., Guyon, I.M., Vapnik, V.N. (1992). A training algorithm for optimal margin classifiers. In: Proceedings of the 5th annual workshop on Computational learning theory, pp. 144\u2013152.","DOI":"10.1145\/130385.130401"},{"key":"1533_CR7","doi-asserted-by":"crossref","unstructured":"Cadena, C., & Ko\u0161eck\u00e1, J. (2014). Semantic segmentation with heterogeneous sensor coverages. In: ICRA, pp. 2639\u20132645.","DOI":"10.1109\/ICRA.2014.6907237"},{"key":"1533_CR8","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., & Ferrari, V. (2018). Coco-stuff: Thing and stuff classes in context. In: CVPR, pp. 1209\u20131218.","DOI":"10.1109\/CVPR.2018.00132"},{"key":"1533_CR9","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N., & Ma, T. (2019). Learning imbalanced datasets with label-distribution-aware margin loss. In: NIPS, pp. 1567\u20131578."},{"issue":"4","key":"1533_CR10","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L Chen","year":"2017","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine intelligence"},{"key":"1533_CR11","doi-asserted-by":"crossref","unstructured":"Chen, L. C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1533_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, B., Chen, L. C., Wei, Y., Zhu, Y., Huang, Z., Xiong, J., Huang, T. S., Hwu, W. M., & Shi, H. (2019). Spgnet: Semantic prediction guidance for scene parsing. In: ICCV, pp. 5218\u20135228.","DOI":"10.1109\/ICCV.2019.00532"},{"key":"1533_CR13","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, J. T., & Choo, J. (2020). Cars can\u2019t fly up in the sky: Improving urban-scene segmentation via height-driven attention networks. In: CVPR, pp. 9373\u20139383.","DOI":"10.1109\/CVPR42600.2020.00939"},{"key":"1533_CR14","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp.3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"1533_CR15","doi-asserted-by":"crossref","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A. Q., & Wang, G. (2018). Context contrasted feature and gated multi-scale aggregation for scene segmentation. In: CVPR, pp. 2393\u20132402.","DOI":"10.1109\/CVPR.2018.00254"},{"key":"1533_CR16","doi-asserted-by":"publisher","first-page":"3520","DOI":"10.1109\/TIP.2019.2962685","volume":"29","author":"H Ding","year":"2020","unstructured":"Ding, H., Jiang, X., Shuai, B., Liu, A. Q., & Wang, G. (2020). Semantic segmentation with context encoding and multi-path decoding. IEEE Transactions on Image Processing, 29, 3520\u20133533.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"11","key":"1533_CR17","doi-asserted-by":"publisher","first-page":"3679","DOI":"10.1109\/TMI.2020.3002417","volume":"39","author":"T Eelbode","year":"2020","unstructured":"Eelbode, T., Bertels, J., Berman, M., Vandermeulen, D., Maes, F., Bisschops, R., & Blaschko, M. B. (2020). Optimization for medical image segmentation: Theory and practice when evaluating with dice score or jaccard index. IEEE Transactions on Medical Imaging, 39(11), 3679\u20133690.","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"1","key":"1533_CR18","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S. A., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98\u2013136.","journal-title":"International Journal of Computer Vision"},{"key":"1533_CR19","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019). Dual attention network for scene segmentation. In: CVPR, pp. 3146\u20133154.","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1533_CR20","unstructured":"Grabocka, J., Scholz, R., Schmidt-Thieme, L. (2019). Learning surrogate losses. CoRR"},{"key":"1533_CR21","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Bourdev, L., Maji, S., & Malik, J. (2011). Semantic contours from inverse detectors. In: ICCV, pp. 991\u2013998.","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"1533_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1533_CR23","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In: CVPR, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"2","key":"1533_CR24","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1109\/TMI.2019.2930068","volume":"39","author":"D Karimi","year":"2019","unstructured":"Karimi, D., & Salcudean, S. E. (2019). Reducing the hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Transactions on Medical Imaging, 39(2), 499\u2013513.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"1533_CR25","doi-asserted-by":"crossref","unstructured":"Ke, T., Hwang, J., Liu, Z., & Yu, S. (2018). Adaptive affinity fields for semantic segmentation. In: ECCV, pp. 587\u2013602.","DOI":"10.1007\/978-3-030-01246-5_36"},{"key":"1533_CR26","unstructured":"Kervadec, H., Bouchtiba, J., Desrosiers, C., Granger, E., Dolz, J., & Ayed, I. B. (2019). Boundary loss for highly unbalanced segmentation. In: MIDL, pp. 285\u2013296."},{"key":"1533_CR27","doi-asserted-by":"crossref","unstructured":"Khan, S., Hayat, M., Zamir, S. W., Shen, J., & Shao, L. (2019). Striking the right balance with uncertainty. In: CVPR, pp. 103\u2013112.","DOI":"10.1109\/CVPR.2019.00019"},{"key":"1533_CR28","unstructured":"Li, Y., Zaragoza, H., Herbrich, R., Shawe-Taylor, J., & Kandola, J. (2002). The perceptron algorithm with uneven margins. In: ICML, pp. 379\u2013386."},{"key":"1533_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In: CVPR, pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1533_CR30","unstructured":"Liu, X., Wang, Y., Wang, L., et al. (2019). Mcdiarmid-type inequalities for graph-dependent variables and stability bounds. In: NIPS, pp. 10890\u201310901."},{"key":"1533_CR31","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1533_CR32","unstructured":"Loshchilov, I., Hutter, F. (2019). Decoupled weight decay regularization. In: ICLR."},{"key":"1533_CR33","doi-asserted-by":"publisher","first-page":"102035","DOI":"10.1016\/j.media.2021.102035","volume":"71","author":"J Ma","year":"2021","unstructured":"Ma, J., Chen, J., Ng, M., Huang, R., Li, Y., Li, C., Yang, X., & Martel, A. L. (2021). Loss odyssey in medical image segmentation. Medical Image Analysis, 71, 102035.","journal-title":"Medical Image Analysis"},{"key":"1533_CR34","volume-title":"Foundations of machine learning","author":"M Mohri","year":"2018","unstructured":"Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018). Foundations of machine learning. London: MIT Press."},{"key":"1533_CR35","unstructured":"Nagendar, G., Singh, D., Balasubramanian, V.N., Jawahar, C. (2018). Neuro-iou: Learning a surrogate loss for semantic segmentation. In: BMVC, p. 278."},{"key":"1533_CR36","doi-asserted-by":"crossref","unstructured":"Neuhold, G., Ollmann, T., Rota Bulo, S., & Kontschieder, P. (2017). The mapillary vistas dataset for semantic understanding of street scenes. In: CVPR, pp. 4990\u20134999.","DOI":"10.1109\/ICCV.2017.534"},{"key":"1533_CR37","unstructured":"Neyshabur, B., Li, Z., Bhojanapalli, S., LeCun, Y., Srebro, N. (2018). The role of over-parametrization in generalization of neural networks. In: ICLR."},{"key":"1533_CR38","doi-asserted-by":"crossref","unstructured":"Nowozin, S. (2014). Optimal decisions from probabilistic models: The intersection-over-union case. In: CVPR, pp. 548\u2013555.","DOI":"10.1109\/CVPR.2014.77"},{"key":"1533_CR39","doi-asserted-by":"crossref","unstructured":"Rahman, M. A., & Wang, Y. (2016). Optimizing intersection-over-union in deep neural networks for image segmentation. In: International symposium on visual computing, pp. 234\u2013244.","DOI":"10.1007\/978-3-319-50835-1_22"},{"key":"1533_CR40","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In: MICCAI, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"1533_CR41","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"1533_CR42","doi-asserted-by":"crossref","unstructured":"Salehi, S. S. M., Erdogmus, D., & Gholipour, A. (2017). Tversky loss function for image segmentation using 3d fully convolutional deep networks. In: International Workshop on Machine Learning in Medical Imaging, pp. 379\u2013387.","DOI":"10.1007\/978-3-319-67389-9_44"},{"key":"1533_CR43","unstructured":"Shen, D., Ji, Y., Li, P., Wang, Y., Lin, D. (2020). Ranet: Region attention network for semantic segmentation. In: NIPS."},{"key":"1533_CR44","doi-asserted-by":"crossref","unstructured":"Sudre, C. H., Li, W., Vercauteren, T., Ourselin, S., & Cardoso, M. J. (2017). Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Deep learning in medical image analysis and multimodal learning for clinical decision support, pp. 240\u2013248.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"1533_CR45","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017). Revisiting unreasonable effectiveness of data in deep learning era. In: CVPR, pp. 843\u2013852.","DOI":"10.1109\/ICCV.2017.97"},{"issue":"8","key":"1533_CR46","doi-asserted-by":"publisher","first-page":"2653","DOI":"10.1109\/TMI.2020.3000314","volume":"39","author":"G Wang","year":"2020","unstructured":"Wang, G., Liu, X., Li, C., Xu, Z., Ruan, J., Zhu, H., Meng, T., Li, K., Huang, N., & Zhang, S. (2020). A noise-robust framework for automatic segmentation of covid-19 pneumonia lesions from ct images. IEEE Transactions on Medical Imaging, 39(8), 2653\u20132663.","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"10","key":"1533_CR47","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J Wang","year":"2020","unstructured":"Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., et al. (2020). Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern analysis and Machine Intelligence, 43(10), 3349\u20133364.","journal-title":"IEEE Transactions on Pattern analysis and Machine Intelligence"},{"key":"1533_CR48","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, D., Zhu, Y., Tian, L., & Shan, Y. (2020). Dual super-resolution learning for semantic segmentation. In: CVPR, pp. 3774\u20133783.","DOI":"10.1109\/CVPR42600.2020.00383"},{"key":"1533_CR49","doi-asserted-by":"crossref","unstructured":"Wong, K. C., Moradi, M., Tang, H., & Syeda-Mahmood, T. (2018). 3d segmentation with exponential logarithmic loss for highly unbalanced object sizes. In: MICCAI, pp. -619.","DOI":"10.1007\/978-3-030-00931-1_70"},{"key":"1533_CR50","unstructured":"Xiao, J., & Quan, L. (2009). Multiple view semantic segmentation for street view images. In ICCV, pp. -693."},{"key":"1533_CR51","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018). Unified perceptual parsing for scene understanding. In: ECCV pp. 418\u2013334","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"1533_CR52","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X., & Sebe, N. (2018). Pad-net: Multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In CVPR p. 675\u2013684","DOI":"10.1109\/CVPR.2018.00077"},{"key":"1533_CR53","unstructured":"Xuhong, L., Grandvalet, Y., & Davoine, F. (2018). Explicit inductive bias for transfer learning with convolutional networks. In: ICML,pp. 2825\u20132834"},{"key":"1533_CR54","doi-asserted-by":"crossref","unstructured":"Yu, F., Chen, H., Wang, X., Xian, W., Chen, Y., Liu, F., Madhavan, V., & Darrell, T. (2020). Bdd100k: A diverse driving dataset for heterogeneous multitask learning. In: CVPR, pp. 2636\u20132645","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"1533_CR55","unstructured":"Yu, F., Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. CoRR."},{"key":"1533_CR56","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017). Pyramid scene parsing network. In: CVPR, pp. 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"1533_CR57","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Y., Liu, S., Shi, J., Change Loy, C., Lin, D., & Jia, J. (2018). Psanet: Point-wise spatial attention network for scene parsing. In: ECCV pp.267-283.","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"1533_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017). Scene parsing through ade20k dataset. In: CVPR, pp. 633\u2013641.","DOI":"10.1109\/CVPR.2017.544"},{"issue":"3","key":"1533_CR59","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., & Torralba, A. (2019). Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127(3), 302\u2013321.","journal-title":"International Journal of Computer Vision"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01533-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-021-01533-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-021-01533-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:04:39Z","timestamp":1641499479000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-021-01533-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,9]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["1533"],"URL":"https:\/\/doi.org\/10.1007\/s11263-021-01533-0","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,9]]},"assertion":[{"value":"24 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}