{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T08:38:10Z","timestamp":1789720690081,"version":"4.0.1"},"reference-count":38,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","funder":[{"name":"Maths4DL","award":["EP\/V026259\/1"],"award-info":[{"award-number":["EP\/V026259\/1"]}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V029428\/1"],"award-info":[{"award-number":["EP\/V029428\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V026259\/1"],"award-info":[{"award-number":["EP\/V026259\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/S026045\/1"],"award-info":[{"award-number":["EP\/S026045\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T003553\/1"],"award-info":[{"award-number":["EP\/T003553\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N014588\/1"],"award-info":[{"award-number":["EP\/N014588\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/T017961\/1"],"award-info":[{"award-number":["EP\/T017961\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong Research Grants Council","award":["RFS2021-5S03"],"award-info":[{"award-number":["RFS2021-5S03"]}]},{"name":"Hong Kong Research Grants Council","award":["15302122"],"award-info":[{"award-number":["15302122"]}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","award":["1-9BCT"],"award-info":[{"award-number":["1-9BCT"]}],"id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Philip Leverhulme Prize"},{"name":"Royal Society Wolfson Fellowship"},{"name":"Wellcome Innovator","award":["215733\/Z\/19\/Z"],"award-info":[{"award-number":["215733\/Z\/19\/Z"]}]},{"name":"Wellcome Innovator","award":["221633\/Z\/20\/Z"],"award-info":[{"award-number":["221633\/Z\/20\/Z"]}]},{"name":"European Union Horizon 2020","award":["777826 NoMADS"],"award-info":[{"award-number":["777826 NoMADS"]}]},{"name":"Cantab Capital Institute for the Mathematics of Information"},{"DOI":"10.13039\/100012338","name":"Alan Turing Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012338","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIHR Cambridge Biomedical Research Centre","award":["NIHR203312"],"award-info":[{"award-number":["NIHR203312"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM Journal on Mathematics of Data Science"],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>Traditional image processing methods employing PDEs offer a multitude of meaningful regularizers along with valuable theoretical foundations for a wide range of image-related tasks. This makes their integration into neural networks a promising avenue. In this paper, we introduce a novel regularization approach inspired by the reverse process of PDE-based evolution models. Specifically, we propose inverse evolution layers (IELs), which serve as bad property amplifiers to penalize neural networks of which outputs have undesired characteristics. Using IELs, one can achieve specific regularization objectives and endow neural network outputs with corresponding properties of the PDE models. Our experiments, focusing on semantic segmentation tasks using heat-diffusion IELs, demonstrate their effectiveness in mitigating noisy label effects. Additionally, we develop curve-motion IELs to enforce convex shape regularization in neural network\u2013based segmentation models for preventing the generation of concave outputs. Our results indicate that IELs may offer a potential regularization mechanism for addressing challenges related to noisy labels.<\/jats:p>","DOI":"10.1137\/24m1633662","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T04:01:26Z","timestamp":1735876886000},"page":"55-85","source":"Crossref","is-referenced-by-count":6,"title":["Inverse Evolution Layers: Physics-Informed Regularizers for Image Segmentation"],"prefix":"10.1137","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2432-3758","authenticated-orcid":true,"given":"Chaoyu","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge CB3 0WA, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0553-1404","authenticated-orcid":true,"given":"Zhonghua","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Research Institute for Smart Energy, The Hong Kong Polytechnic University, Hong Kong, People\u2019s Republic of China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge CB3 0WA, UK, and School of Science and Engineering and School of Medicine, University of Dundee, Dundee DD1 4HN, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carola-Bibiane","family":"Sch\u00f6nlieb","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge CB3 0WA, UK."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"Badrinarayanan V.","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/16M1070426"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1038\/s41592-019-0612-7","volume":"16","author":"Caicedo J. C.","year":"2019","journal-title":"Nat. Methods"},{"key":"ref4","doi-asserted-by":"crossref","unstructured":"N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, End-to-end object detection with transformers, in Computer Vision\u2014ECCV 2020: 16th European Conference, Proceedings, Part I, 2020, pp. 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1017\/S0956792521000139","volume":"32","author":"Celledoni E.","year":"2021","journal-title":"Eur. J. Appl. Math."},{"key":"ref6","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1109\/83.902291","volume":"10","author":"Chan T. F.","year":"2001","journal-title":"IEEE Trans. Image Process."},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, Encoder-decoder with atrous separable convolution for semantic image segmentation, in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 801\u2013818.","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"X. Chen, B. M. Williams, S. R. Vallabhaneni, G. Czanner, R. Williams, and Y. Zheng, Learning active contour models for medical image segmentation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 11632\u201311640.","DOI":"10.1109\/CVPR.2019.01190"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Y. Chen, W. Yu, and T. Pock, On learning optimized reaction diffusion processes for effective image restoration, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 5261\u20135269.","DOI":"10.1109\/CVPR.2015.7299163"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"D. Cheng, R. Liao, S. Fidler, and R. Urtasun, DARNet: Deep active ray network for building segmentation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 7431\u20137439.","DOI":"10.1109\/CVPR.2019.00761"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, The Cityscapes dataset for semantic urban scene understanding, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 3213\u20133223.","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref12","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly,\n                      J. Uszkoreit, and N. Houlsby\n                      , An image is worth 16x16 words: Transformers for image recognition at scale, in International Conference on Learning Representations, Virtual Event, Austria, May 3-7, 2021, OpenReview.net, 2021, 617, https:\/\/openreview.net\/forum?id=YicbFdNTTy."},{"key":"ref13","unstructured":"A. Hatamizadeh, D. Sengupta, and D. Terzopoulos, End-to-End Deep Convolutional Active Contours for Image Segmentation, preprint, arXiv:1909.13359, 2019."},{"key":"ref14","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"Isensee F.","year":"2021","journal-title":"Nat. Methods"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/21M1421830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/22M1483645"},{"key":"ref17","unstructured":"J. Liu, X.C. Tai, and S. Luo, Convex Shape Prior for Deep Neural Convolution Network Based Eye Fundus Images Segmentation, preprint, arXiv:2005.07476, 2020."},{"key":"ref18","first-page":"1","volume":"64","author":"Liu J.","year":"2022","journal-title":"J. Math. Imaging Vision"},{"key":"ref19","unstructured":"Y. Lu, A. Zhong, Q. Li, and B. Dong, Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations, in International Conference on Machine Learning, PMLR, 2018, pp. 3276\u20133285."},{"key":"ref20","unstructured":"S. Lunz, O. \u00d6ktem, and C.B. Sch\u00f6nlieb, Adversarial regularizers in inverse problems, in Proceedings of 32nd Conference on Neural Information Processing Systems (NeurIPS), Montreal, PQ, Canada, 2018, pp. 8507\u20138516."},{"key":"ref21","unstructured":"S. Luo, X.C. Tai, and Y. Wang, Convex Shape Representation with Binary Labels for Image Segmentation: Models and Fast Algorithms, preprint, arXiv:2002.09600, 2020."},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"D. Marcos, D. Tuia, B. Kellenberger, L. Zhang, M. Bai, R. Liao, and R. Urtasun, Learning deep structured active contours end-to-end, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8877\u20138885.","DOI":"10.1109\/CVPR.2018.00925"},{"key":"ref23","volume-title":"Variational Methods in Image Segmentation: With Seven Image Processing Experiments","volume":"14","author":"Morel J.-M.","year":"2012"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1002\/cpa.3160420503","volume":"42","author":"Mumford D. B.","year":"1989","journal-title":"Comm. Pure Appl. Math."},{"key":"ref25","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/0262-8856(90)80008-H","volume":"8","author":"Nordstr\u00f6m K. N.","year":"1990","journal-title":"Image Vision Comput."},{"key":"ref26","doi-asserted-by":"crossref","first-page":"101570","DOI":"10.1016\/j.media.2019.101570","volume":"59","author":"Orlando J. I.","year":"2020","journal-title":"Med. Image Anal."},{"key":"ref27","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/0021-9991(88)90002-2","volume":"79","author":"Osher S.","year":"1988","journal-title":"J. Comput. Phys."},{"key":"ref28","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1109\/34.56205","volume":"12","author":"Perona P.","year":"1990","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref29","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","volume":"378","author":"Raissi M.","year":"2019","journal-title":"J. Comput. Phys."},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, and T. Brox, U-net: Convolutional networks for biomedical image segmentation, in Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015: 18th International Conference, Proceedings, Part III, Springer-Verlag, Berlin, 2015, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1007\/s10851-019-00903-1","volume":"62","author":"Ruthotto L.","year":"2020","journal-title":"J. Math. Imaging Vision"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1109\/TMI.2004.825627","volume":"23","author":"Staal J.","year":"2004","journal-title":"IEEE Trans. Med. Imag."},{"key":"ref33","unstructured":"K. Sun, Y. Zhao, B. Jiang, T. Cheng, B. Xiao, D. Liu, Y. Mu, X. Wang, W. Liu, and J. Wang, High-Resolution Representations for Labeling Pixels and Regions, preprint, arXiv:1904.04514, 2019."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/23M1586355"},{"key":"ref35","volume-title":"Anisotropic Diffusion in Image Processing","volume":"1","author":"Weickert J.","year":"1998"},{"key":"ref36","first-page":"1","volume":"1","author":"Weinan E.","year":"2017","journal-title":"Commun. Math. Stat."},{"key":"ref37","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"Zhang C.","year":"2021","journal-title":"Commun. ACM"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.micron.2018.01.010","volume":"107","author":"Zheng X.","year":"2018","journal-title":"Micron"}],"container-title":["SIAM Journal on Mathematics of Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/24M1633662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:24:06Z","timestamp":1787325846000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/24M1633662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,3]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1137\/24M1633662"],"URL":"https:\/\/doi.org\/10.1137\/24m1633662","relation":{},"ISSN":["2577-0187"],"issn-type":[{"value":"2577-0187","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,3]]}}}