{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:21:53Z","timestamp":1781587313433,"version":"3.54.5"},"reference-count":101,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,7,27]],"date-time":"2022-07-27T00:00:00Z","timestamp":1658880000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,7,27]],"date-time":"2022-07-27T00:00:00Z","timestamp":1658880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Math Imaging Vis"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the layer\u2019s trainable weights. Formulating our PDEs on homogeneous spaces allows these networks to be designed with built-in symmetries such as rotation in addition to the standard translation equivariance of CNNs. Having all the desired symmetries included in the design obviates the need to include them by means of costly techniques such as data augmentation. We will discuss our PDE-based G-CNNs (PDE-G-CNNs) in a general homogeneous space setting while also going into the specifics of our primary case of interest: roto-translation equivariance. We solve the PDE of interest by a combination of linear group convolutions and nonlinear morphological group convolutions with analytic kernel approximations that we underpin with formal theorems. Our kernel approximations allow for fast GPU-implementation of the PDE-solvers; we release our implementation with this article in the form of the LieTorch extension to PyTorch, available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/gitlab.com\/bsmetsjr\/lietorch\">https:\/\/gitlab.com\/bsmetsjr\/lietorch<\/jats:ext-link>. Just like for linear convolution, a morphological convolution is specified by a kernel that we train in our PDE-G-CNNs. In PDE-G-CNNs, we do not use non-linearities such as max\/min-pooling and ReLUs as they are already subsumed by morphological convolutions. We present a set of experiments to demonstrate the strength of the proposed PDE-G-CNNs in increasing the performance of deep learning-based imaging applications with far fewer parameters than traditional CNNs.<\/jats:p>","DOI":"10.1007\/s10851-022-01114-x","type":"journal-article","created":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T01:38:22Z","timestamp":1658972302000},"page":"209-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["PDE-Based Group Equivariant Convolutional Neural Networks"],"prefix":"10.1007","volume":"65","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8480-0782","authenticated-orcid":false,"given":"Bart M. N.","family":"Smets","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jim","family":"Portegies","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik J.","family":"Bekkers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Remco","family":"Duits","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,27]]},"reference":[{"key":"1114_CR1","doi-asserted-by":"crossref","unstructured":"Welk, M., Weickert, J.: PDE evolutions for M-smoothers: from common myths to robust numerics. In: International Conference on Scale Space and Variational Methods in Computer Vision, pp. 236\u2013248. Springer (2019)","DOI":"10.1007\/978-3-030-22368-7_19"},{"issue":"3","key":"1114_CR2","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s10851-015-0577-9","volume":"52","author":"J Fadili","year":"2015","unstructured":"Fadili, J., Kutyniok, G., Peyr\u00e9, G., Plonka-Hoch, G., Steidl, G.: Guest editorial: mathematics and image analysis. J. Math. Imaging Vis. 52(3), 315\u2013316 (2015)","journal-title":"J. Math. Imaging Vis."},{"issue":"3","key":"1114_CR3","first-page":"197","volume":"5","author":"G Peyr\u00e9","year":"2010","unstructured":"Peyr\u00e9, G., P\u00e9chaud, M., Keriven, R., Cohen, L.D.: Geodesic methods in computer vision and graphics. Found. Trends. Comput. Graph. Vis. 5(3), 197\u2013397 (2010)","journal-title":"Found. Trends. Comput. Graph. Vis."},{"issue":"8","key":"1114_CR4","doi-asserted-by":"publisher","first-page":"1585","DOI":"10.1109\/TPAMI.2014.2385708","volume":"37","author":"A Dubrovina-Karni","year":"2015","unstructured":"Dubrovina-Karni, A., Rosman, G., Kimmel, R.: Multi-region active contours with a single level set function. IEEE PAMI 37(8), 1585\u20131601 (2015)","journal-title":"IEEE PAMI"},{"key":"1114_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41589-5_10","volume-title":"First Order Algorithms in Variational Image Processing","author":"M Burger","year":"2016","unstructured":"Burger, M., Sawatzky, A., Steidl, G.: First Order Algorithms in Variational Image Processing. Springer, Cham (2016)"},{"issue":"1","key":"1114_CR6","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1137\/15M102873X","volume":"9","author":"J Duran","year":"2016","unstructured":"Duran, J., Moeller, M., Sbert, C., Cremers, D.: Collaborative total variation: a general framework for vectorial tv models. SIAM SIIMS 9(1), 116\u2013151 (2016)","journal-title":"SIAM SIIMS"},{"issue":"3","key":"1114_CR7","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s11263-015-0874-1","volume":"118","author":"J Weickert","year":"2016","unstructured":"Weickert, J., Grewenig, S., Schroers, C., Bruhn, A.: Cyclic schemes for PDE-based image analysis. Int. J. Comput. Vis. 118(3), 275\u2013299 (2016)","journal-title":"Int. J. Comput. Vis."},{"key":"1114_CR8","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511626319","volume-title":"Geometric Partial Differential Equations and Image Analysis","author":"G Sapiro","year":"2001","unstructured":"Sapiro, G.: Geometric Partial Differential Equations and Image Analysis. Cambridge University Press, Cambridge (2001). https:\/\/doi.org\/10.1017\/CBO9780511626319"},{"key":"1114_CR9","volume-title":"Level Set Methods and Fast Marching Methods","author":"J Sethian","year":"1999","unstructured":"Sethian, J.: Level Set Methods and Fast Marching Methods. Cambridge University Press, Cambridge (1999)"},{"key":"1114_CR10","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/978-3-7091-6586-7_13","volume":"11","author":"J Weickert","year":"1996","unstructured":"Weickert, J.: Theoretical foundations of anisotropic diffusion in image processing. Comput. Suppl. 11, 221\u2013236 (1996)","journal-title":"Comput. Suppl."},{"key":"1114_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-0567-5","volume-title":"Variational Methods in Image Segmentation: With Seven Image Processing Experiments. Progress in Nonlinear Differential Equations and Their Applications","author":"J Morel","year":"1995","unstructured":"Morel, J., Solimini, S.: Variational Methods in Image Segmentation: With Seven Image Processing Experiments. Progress in Nonlinear Differential Equations and Their Applications. Birkh\u00e4user, Basel (1995)"},{"key":"1114_CR12","doi-asserted-by":"crossref","unstructured":"Duits, R., Burgeth, B.: Scale spaces on Lie groups. In: International Conference on Scale Space and Variational Methods in Computer Vision, pp. 300\u2013312. Springer (2007)","DOI":"10.1007\/978-3-540-72823-8_26"},{"key":"1114_CR13","unstructured":"Cohen, T.S., Welling, M.: Group equivariant convolutional networks. In: International of Conference on Machine Learning, pp. 2990\u20132999 (2016)"},{"key":"1114_CR14","unstructured":"Dieleman, S., De\u00a0Fauw, J., Kavukcuoglu, K.: Exploiting cyclic symmetry in convolutional neural networks (2016). arXiv preprint arXiv:1602.02660"},{"issue":"2","key":"1114_CR15","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.1093\/mnras\/stv632","volume":"450","author":"S Dieleman","year":"2015","unstructured":"Dieleman, S., Willett, K.W., Dambre, J.: Rotation-invariant convolutional neural networks for galaxy morphology prediction. Mon. Not. R. Astron. Soc. 450(2), 1441\u20131459 (2015)","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"1114_CR16","unstructured":"Winkels, M., Cohen, T.S.: 3D G-CNNs for pulmonary nodule detection (2018). arXiv preprint arXiv:1804.04656"},{"key":"1114_CR17","doi-asserted-by":"crossref","unstructured":"Worrall, D., Brostow, G.: Cubenet: Equivariance to 3D rotation and translation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 567\u2013584 (2018)","DOI":"10.1007\/978-3-030-01228-1_35"},{"issue":"2","key":"1114_CR18","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1109\/TPAMI.2017.2652452","volume":"40","author":"EJ Bekkers","year":"2017","unstructured":"Bekkers, E.J., Loog, M., ter Haar Romeny, B.M., Duits, R.: Template matching via densities on the roto-translation group. IEEE Trans. Pattern Anal. Mach. Intell. 40(2), 452\u2013466 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1114_CR19","doi-asserted-by":"crossref","unstructured":"Oyallon, E., Mallat, S.: Deep roto-translation scattering for object classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2865\u20132873 (2015)","DOI":"10.1109\/CVPR.2015.7298904"},{"key":"1114_CR20","doi-asserted-by":"crossref","unstructured":"Bekkers, E.J., Lafarge, M.W., Veta, M., Eppenhof, K.A., Pluim, J.P., Duits, R.: Roto-translation covariant convolutional networks for medical image analysis. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 440\u2013448. Springer (2018). arXiv:1804.03393","DOI":"10.1007\/978-3-030-00928-1_50"},{"key":"1114_CR21","doi-asserted-by":"crossref","unstructured":"Weiler, M., Hamprecht, F.A., Storath, M.: Learning steerable filters for rotation equivariant cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 849\u2013858 (2018)","DOI":"10.1109\/CVPR.2018.00095"},{"key":"1114_CR22","unstructured":"Cohen, T.S., Geiger, M., Weiler, M.: A general theory of equivariant cnns on homogeneous spaces. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"1114_CR23","doi-asserted-by":"crossref","unstructured":"Worrall, D.E., Garbin, S.J., Turmukhambetov, D., Brostow, G.J.: Harmonic networks: deep translation and rotation equivariance. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5028\u20135037 (2017)","DOI":"10.1109\/CVPR.2017.758"},{"key":"1114_CR24","unstructured":"Kondor, R., Trivedi, S.: On the generalization of equivariance and convolution in neural networks to the action of compact groups. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a080, pp. 2747\u20132755. PMLR, Stockholmsm\u00e4ssan, Stockholm Sweden (2018). http:\/\/proceedings.mlr.press\/v80\/kondor18a.html"},{"key":"1114_CR25","doi-asserted-by":"crossref","unstructured":"Esteves, C., Allen-Blanchette, C., Makadia, A., Daniilidis, K.: Learning SO(3) equivariant representations with spherical CNNs. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 52\u201368 (2018)","DOI":"10.1007\/978-3-030-01261-8_4"},{"key":"1114_CR26","doi-asserted-by":"crossref","unstructured":"Akian, M., Quadrat, J.P., Viot, M.: Bellman processes. In: 11th International Conference on Analysis and Optimization of Systems Discrete Event Systems, pp. 302\u2013311. Springer (1994)","DOI":"10.1007\/BFb0033561"},{"key":"1114_CR27","doi-asserted-by":"crossref","unstructured":"Burgeth, B., Welk, M., Feddern, C., Weickert, J.: Morphological operations on matrix-valued images. In: European Conference on Computer Vision, pp. 155\u2013167. Springer (2004)","DOI":"10.1007\/978-3-540-24673-2_13"},{"issue":"3","key":"1114_CR28","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1007\/s10851-012-0387-2","volume":"46","author":"R Duits","year":"2013","unstructured":"Duits, R., Haije, T.D., Creusen, E., Ghosh, A.: Morphological and linear scale spaces for fiber enhancement in DW-MRI. J. Math. Imaging Vis. 46(3), 326\u2013368 (2013)","journal-title":"J. Math. Imaging Vis."},{"issue":"4","key":"1114_CR29","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1137\/15M1018460","volume":"8","author":"EJ Bekkers","year":"2015","unstructured":"Bekkers, E.J., Duits, R., Mashtakov, A., Sanguinetti, G.R.: A PDE approach to data-driven sub-Riemannian geodesics in SE(2). SIAM J. Imaging Sci. 8(4), 2740\u20132770 (2015)","journal-title":"SIAM J. Imaging Sci."},{"key":"1114_CR30","doi-asserted-by":"crossref","unstructured":"Haije, T.C.D., Duits, R., Tax, C.M.: Sharpening fibers in diffusion weighted MRI via erosion. In: Visualization and Processing of Tensors and Higher Order Descriptors for Multi-valued Data, pp. 97\u2013126. Springer (2014)","DOI":"10.1007\/978-3-642-54301-2_5"},{"key":"1114_CR31","first-page":"27","volume":"12679","author":"R Duits","year":"2021","unstructured":"Duits, R., Smets, B., Bekkers, E.J., Portegies, J.M.: Equivariant deep learning via morphological and linear scale space PDEs on the space of positions and orientations. LNCS 12679, 27\u201339 (2021)","journal-title":"LNCS"},{"issue":"1","key":"1114_CR32","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1137\/15M1013572","volume":"9","author":"G Citti","year":"2016","unstructured":"Citti, G., Franceschiello, B., Sanguinetti, G., Sarti, A.: Sub-Riemannian mean curvature flow for image processing. SIAM J. Imaging Sci. 9(1), 212\u2013237 (2016)","journal-title":"SIAM J. Imaging Sci."},{"issue":"1","key":"1114_CR33","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1007\/s10851-010-0251-1","volume":"40","author":"A Chambolle","year":"2011","unstructured":"Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120\u2013145 (2011)","journal-title":"J. Math. Imaging Vis."},{"issue":"3","key":"1114_CR34","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s00211-019-01026-w","volume":"142","author":"A Chambolle","year":"2019","unstructured":"Chambolle, A., Pock, T.: Total roto-translational variation. Numer. Math. 142(3), 611\u2013666 (2019). https:\/\/doi.org\/10.1007\/s00211-019-01026-w","journal-title":"Numer. Math."},{"issue":"2","key":"1114_CR35","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s10851-020-00991-4","volume":"63","author":"BM Smets","year":"2021","unstructured":"Smets, B.M., Portegies, J., St-Onge, E., Duits, R.: Total variation and mean curvature PDEs on the homogeneous space of positions and orientations. J. Math. Imaging Vis. 63(2), 237\u2013262 (2021)","journal-title":"J. Math. Imaging Vis."},{"issue":"1","key":"1114_CR36","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1134\/S1054661807010063","volume":"17","author":"R Duits","year":"2007","unstructured":"Duits, R., Duits, M., van Almsick, M., ter Haar Romeny, B.: Invertible orientation scores as an application of generalized wavelet theory. Pattern Recognit. Image Anal. 17(1), 42\u201375 (2007)","journal-title":"Pattern Recognit. Image Anal."},{"issue":"9","key":"1114_CR37","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.1007\/s10851-018-0806-0","volume":"60","author":"MHJ Janssen","year":"2018","unstructured":"Janssen, M.H.J., Janssen, A.J.E.M., Bekkers, E.J., Besc\u00f3s, J.O., Duits, R.: Design and processing of invertible orientation scores of 3D images. J. Math. Imaging Vis. 60(9), 1427\u20131458 (2018). https:\/\/doi.org\/10.1007\/s10851-018-0806-0","journal-title":"J. Math. Imaging Vis."},{"key":"1114_CR38","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.difgeo.2019.03.007","volume":"65","author":"B Franceschiello","year":"2019","unstructured":"Franceschiello, B., Mashtakov, A., Citti, G., Sarti, A.: Geometrical optical illusion via sub-Riemannian geodesics in the roto-translation group. Differ. Geom. Appl. 65, 55\u201377 (2019)","journal-title":"Differ. Geom. Appl."},{"issue":"3","key":"1114_CR39","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s10851-005-3630-2","volume":"24","author":"G Citti","year":"2006","unstructured":"Citti, G., Sarti, A.: A cortical based model of perceptional completion in the roto-translation space. J. Math. Imaging Vis. 24(3), 307\u2013326 (2006)","journal-title":"J. Math. Imaging Vis."},{"key":"1114_CR40","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1090\/S0033-569X-10-01172-0","volume":"68","author":"R Duits","year":"2010","unstructured":"Duits, R., Franken, E.M.: Left invariant parabolic evolution equations on SE(2) and contour enhancement via invertible orientation scores, part I: linear left-invariant diffusion equations on SE(2). Q. Appl. Math. 68, 255\u2013292 (2010)","journal-title":"Q. Appl. Math."},{"key":"1114_CR41","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1090\/S0033-569X-10-01173-3","volume":"68","author":"R Duits","year":"2010","unstructured":"Duits, R., Franken, E.M.: Left invariant parabolic evolution equations on SE(2) and contour enhancement via invertible orientation scores, part II: nonlinear left-invariant diffusion equations on invertible orientation scores. Q. Appl. Math. 68, 293\u2013331 (2010)","journal-title":"Q. Appl. Math."},{"issue":"1","key":"1114_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4208\/nmtma.2015.m1411","volume":"9","author":"J Zhang","year":"2016","unstructured":"Zhang, J., Duits, R., ter Haar Romeny, B., Sanguinetti, G.: Numerical approaches for linear left-invariant diffusions on SE(2), their comparisons to exact solutions, and their applications in retinal imaging. Numer. Math. Theory Methods Appl. 9(1), 1\u201350 (2016)","journal-title":"Numer. Math. Theory Methods Appl."},{"issue":"2","key":"1114_CR43","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1137\/130924731","volume":"7","author":"U Boscain","year":"2014","unstructured":"Boscain, U., Chertovskih, R.A., Gauthier, J.P., Remizov, A.O.: Hypoelliptic diffusion and human vision: a semidiscrete new twist. SIAM J. Imaging Sci. 7(2), 669\u2013695 (2014)","journal-title":"SIAM J. Imaging Sci."},{"key":"1114_CR44","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-030-22368-7_37","volume-title":"Scale Space and Variational Methods in Computer Vision","author":"M Bertalm\u00edo","year":"2019","unstructured":"Bertalm\u00edo, M., Calatroni, L., Franceschi, V., Franceschiello, B., Prandi, D.: A cortical-inspired model for orientation-dependent contrast perception: a link with Wilson-Cowan equations. In: Lellmann, J., Burger, M., Modersitzki, J. (eds.) Scale Space and Variational Methods in Computer Vision, pp. 472\u2013484. Springer, Cham (2019)"},{"issue":"3","key":"1114_CR45","first-page":"483","volume":"35","author":"R Duits","year":"2013","unstructured":"Duits, R., Fuehr, H., Janssen, B., Florack, L., van Assen, H.: Evolution equations on Gabor transforms and their applications. ACHA 35(3), 483\u2013526 (2013)","journal-title":"ACHA"},{"issue":"3","key":"1114_CR46","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s10851-013-0482-z","volume":"49","author":"D Barbieri","year":"2014","unstructured":"Barbieri, D., Citti, G., Cocci, G., Sarti, A.: A cortical-inspired geometry for contour perception and motion integration. J. Math. Imaging Vis. 49(3), 511\u2013529 (2014)","journal-title":"J. Math. Imaging Vis."},{"key":"1114_CR47","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.jphysparis.2003.10.010","volume":"97","author":"J Petitot","year":"2003","unstructured":"Petitot, J.: The neurogeometry of pinwheels as a sub-Riemannian contact structure. J. Physiol. Paris 97, 265\u2013309 (2003)","journal-title":"J. Physiol. Paris"},{"key":"1114_CR48","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/TPAMI.2006.29","volume":"28","author":"M Felsberg","year":"2006","unstructured":"Felsberg, M., Forssen, P.E., Scharr, H.: Channel smoothing: efficient robust smoothing of low-level signal features. IEEE Trans. Pattern Anal. Mach. Intell. 28, 209\u2013222 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"24","key":"1114_CR49","doi-asserted-by":"publisher","first-page":"9248","DOI":"10.1073\/pnas.1120785109","volume":"109","author":"P Savadjiev","year":"2012","unstructured":"Savadjiev, P., Strijkers, G., Bakermans, A., Piuze, E., Zucker, S., Siddiqi, K.: Heart wall myofibers are arranged in minimal surfaces to optimize organ function. PNAS 109(24), 9248\u20139253 (2012)","journal-title":"PNAS"},{"issue":"1","key":"1114_CR50","doi-asserted-by":"publisher","first-page":"38","DOI":"10.3390\/e21010038","volume":"21","author":"R Duits","year":"2019","unstructured":"Duits, R., Bekkers, E., Mashtakov, A.: Fourier transform on the homogeneous space of 3D positions and orientations for exact solutions to linear PDEs. Entropy 21(1), 38 (2019)","journal-title":"Entropy"},{"key":"1114_CR51","doi-asserted-by":"publisher","unstructured":"Momayyez-Siahkal, P., Siddiqi, K.: 3D stochastic completion fields for fiber tractography. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2009). https:\/\/doi.org\/10.1109\/CVPRW.2009.5204044","DOI":"10.1109\/CVPRW.2009.5204044"},{"issue":"3","key":"1114_CR52","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.acha.2012.11.007","volume":"35","author":"R Duits","year":"2013","unstructured":"Duits, R., F\u00fchr, H., Janssen, B., Bruurmijn, M., Florack, L., van Assen, H.: Evolution equations on Gabor transforms and their applications. Appl. Comput. Harmon. Anal. 35(3), 483\u2013526 (2013)","journal-title":"Appl. Comput. Harmon. Anal."},{"issue":"1","key":"1114_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13408-020-00099-4","volume":"11","author":"U Boscain","year":"2021","unstructured":"Boscain, U., Prandi, D., Sacchelli, L., Turco, G.: A bio-inspired geometric model for sound reconstruction. J. Math. Neurosci. 11(1), 1\u201318 (2021)","journal-title":"J. Math. Neurosci."},{"issue":"6","key":"1114_CR54","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1007\/s10851-018-0803-3","volume":"60","author":"E Baspinar","year":"2018","unstructured":"Baspinar, E., Citti, G., Sarti, A.: A geometric model of multi-scale orientation preference maps via Gabor functions. J. Math. Imaging Vis. 60(6), 900\u2013912 (2018)","journal-title":"J. Math. Imaging Vis."},{"key":"1114_CR55","unstructured":"Bekkers, E.J.: B-Spline CNNs on Lie groups. In: International Conference on Learning Representations (2019)"},{"key":"1114_CR56","unstructured":"Finzi, M., Stanton, S., Izmailov, P., Wilson, A.G.: Generalizing convolutional neural networks for equivariance to Lie groups on arbitrary continuous data. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 3165\u20133176. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/finzi20a.html"},{"key":"1114_CR57","unstructured":"Weiler, M., Cesa, G.: General E(2)-equivariant steerable CNNs. In: Advances in Neural Information Processing Systems, pp. 14334\u201314345 (2019)"},{"issue":"6","key":"1114_CR58","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1007\/BF02510697","volume":"6","author":"GS Chirikjian","year":"2000","unstructured":"Chirikjian, G.S., Kyatkin, A.B.: An operational calculus for the Euclidean motion group with applications in robotics and polymer science. J. Fourier Anal. Appl. 6(6), 583\u2013606 (2000)","journal-title":"J. Fourier Anal. Appl."},{"key":"1114_CR59","doi-asserted-by":"crossref","unstructured":"Franken, E., van Almsick, M., Rongen, P., Florack, L., ter Haar\u00a0Romeny, B.: An efficient method for tensor voting using steerable filters. In: European Conference on Computer Vision, pp. 228\u2013240. Springer (2006)","DOI":"10.1007\/11744085_18"},{"key":"1114_CR60","unstructured":"Reisert, M.: Group integration techniques in pattern analysis: a kernel view. Ph.D. thesis, Albert-Ludwigs-Universit\u00e4t Freiburg (2008)"},{"key":"1114_CR61","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1258-4","volume-title":"Coherent States, Wavelets and Their Generalizations","author":"ST Ali","year":"2000","unstructured":"Ali, S.T., Antoine, J.P., Gazeau, J.P., et al.: Coherent States, Wavelets and Their Generalizations, vol. 1. Springer, Berlin (2000)"},{"key":"1114_CR62","unstructured":"Sifre, L., Mallat, S.: Rigid-motion scattering for texture classification (2014). arXiv preprint arXiv:1403.1687"},{"key":"1114_CR63","unstructured":"Finzi, M., Bondesan, R., Welling, M.: Probabilistic numeric convolutional neural networks (2020). arXiv preprint arXiv:2010.10876"},{"key":"1114_CR64","unstructured":"Montobbio, N.: A metric model of the visual cortex. Ph.D. thesis, Universit\u00e0 di Bologna - Sorbonne Universit\u00e9 (2019)"},{"key":"1114_CR65","unstructured":"Montobbio, N., Bonnasse-Gahot, L., Citti, G., Sarti, A.: KerCNNs: biologically inspired lateral connections for classification of corrupted images (2019). arXiv preprint arXiv:1910.08336"},{"issue":"1","key":"1114_CR66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40304-017-0103-z","volume":"5","author":"E Weinan","year":"2017","unstructured":"Weinan, E.: A proposal on machine learning via dynamical systems. Commun. Math. Stat. 5(1), 1\u201311 (2017)","journal-title":"Commun. Math. Stat."},{"key":"1114_CR67","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":"1114_CR68","unstructured":"Lu, Y., Zhong, A., Li, Q., Dong, B.: Beyond finite layer neural networks: bridging deep architectures and numerical differential equations (2017). arXiv preprint arXiv:1710.10121"},{"key":"1114_CR69","unstructured":"Chen, T.Q., Rubanova, Y., Bettencourt, J., Duvenaud, D.K.: Neural ordinary differential equations. In: Advances in Neural Information Processing Systems, pp. 6571\u20136583 (2018)"},{"key":"1114_CR70","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yu, W., Pock, T.: On learning optimized reaction diffusion processes for effective image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5261\u20135269 (2015)","DOI":"10.1109\/CVPR.2015.7299163"},{"key":"1114_CR71","unstructured":"Long, Z., Lu, Y., Ma, X., Dong, B.: PDE-net: Learning PDEs from data (2017). arXiv preprint arXiv:1710.09668"},{"issue":"3","key":"1114_CR72","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1007\/s10851-019-00903-1","volume":"62","author":"L Ruthotto","year":"2020","unstructured":"Ruthotto, L., Haber, E.: Deep neural networks motivated by partial differential equations. J. Math. Imaging Vis. 62(3), 352\u2013364 (2020)","journal-title":"J. Math. Imaging Vis."},{"key":"1114_CR73","unstructured":"Shen, Z., He, L., Lin, Z., Ma, J.: Pdo-econvs: partial differential operator based equivariant convolutions. In: International Conference on Machine Learning, pp. 8697\u20138706. PMLR (2020)"},{"key":"1114_CR74","unstructured":"Weiler, M., Forr\u00e9, P., Verlinde, E., Welling, M.: Coordinate independent convolutional networks\u2014isometry and gauge equivariant convolutions on Riemannian manifolds (2021). arXiv preprint arXiv:2106.06020"},{"key":"1114_CR75","unstructured":"Jenner, E., Weiler, M.: Steerable partial differential operators for equivariant neural networks (2021). arXiv preprint arXiv:2106.10163"},{"issue":"1","key":"1114_CR76","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9a90","volume":"34","author":"E Haber","year":"2017","unstructured":"Haber, E., Ruthotto, L.: Stable architectures for deep neural networks. Inverse Prob. 34(1), 014004 (2017)","journal-title":"Inverse Prob."},{"key":"1114_CR77","doi-asserted-by":"crossref","unstructured":"Alt, T., Peter, P., Weickert, J., Schrader, K.: Translating numerical concepts for PDEs into neural architectures (2021). arXiv preprint arXiv:2103.15419","DOI":"10.1007\/978-3-030-75549-2_24"},{"key":"1114_CR78","unstructured":"Koda, T.: An introduction to the geometry of homogeneous spaces. In: Proceedings of the Thirteenth International Workshop on Differential Geometry, vol.\u00a013, pp. 121\u2013144 (2009)"},{"key":"1114_CR79","first-page":"658","volume":"643","author":"JM Lee","year":"2009","unstructured":"Lee, J.M., Chow, B., Chu, S.C., Glickenstein, D., Guenther, C., Isenberg, J., Ivey, T., Knopf, D., Lu, P., Luo, F., et al.: Manifolds and differential geometry. Topology 643, 658 (2009)","journal-title":"Topology"},{"key":"1114_CR80","unstructured":"Smets, B.: Geometric image denoising and machine learning. Master thesis, TU Eindhoven (2019). https:\/\/bmnsmets.com\/publication\/smets2019msc\/"},{"key":"1114_CR81","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1515\/form.1994.6.111","volume":"6","author":"W Arendt","year":"1994","unstructured":"Arendt, W., Bukhvalov, A.V.: Integral representations of resolvents and semigroups. Forum Math. 6, 111\u2013136 (1994)","journal-title":"Forum Math."},{"key":"1114_CR82","doi-asserted-by":"publisher","DOI":"10.1007\/b104912","volume-title":"Abstract Harmonic Analysis of Continuous Wavelet Transforms. 1863","author":"H F\u00fchr","year":"2005","unstructured":"F\u00fchr, H.: Abstract Harmonic Analysis of Continuous Wavelet Transforms. 1863. Springer, Berlin (2005)"},{"key":"1114_CR83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10851-018-0795-z","volume":"60","author":"R Duits","year":"2018","unstructured":"Duits, R., Meesters, S.P., Mirebeau, J.M., Portegies, J.M.: Optimal paths for variants of the 2D and 3D Reeds\u2013Shepp car with applications in image analysis. J. Math. Imaging Vis. 60, 1\u201333 (2018)","journal-title":"J. Math. Imaging Vis."},{"key":"1114_CR84","doi-asserted-by":"crossref","unstructured":"Portegies, J., Sanguinetti, G., Meesters, S., Duits, R.: New approximation of a scale space kernel on SE(3) and applications in neuroimaging. In: International Conference on Scale Space and Variational Methods in Computer Vision, pp. 40\u201352. Springer (2015)","DOI":"10.1007\/978-3-319-18461-6_4"},{"issue":"1","key":"1114_CR85","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1006\/jfan.1998.3259","volume":"157","author":"A Ter Elst","year":"1998","unstructured":"Ter Elst, A., Robinson, D.W.: Weighted subcoercive operators on Lie groups. J. Funct. Anal. 157(1), 88\u2013163 (1998)","journal-title":"J. Funct. Anal."},{"issue":"1","key":"1114_CR86","first-page":"65","volume":"8","author":"P Maheux","year":"1998","unstructured":"Maheux, P.: Estimations du noyau de la chaleur sur les espaces homogenes. ESAIM Control Optim. Calc. Var. 8(1), 65\u201396 (1998)","journal-title":"ESAIM Control Optim. Calc. Var."},{"key":"1114_CR87","doi-asserted-by":"crossref","unstructured":"Grigor\u2019yan, A., Hu, J., Lau, K.S.: Heat kernels on metric spaces with doubling measure. In: Fractal Geometry and Stochastics IV, pp. 3\u201344. Springer (2009)","DOI":"10.1007\/978-3-0346-0030-9_1"},{"key":"1114_CR88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-11791-0","volume-title":"Functional Analysis","author":"K Yosida","year":"1968","unstructured":"Yosida, K.: Functional Analysis. Springer, Berlin (1968)"},{"key":"1114_CR89","volume-title":"Partial Differential Equations","author":"LC Evans","year":"2010","unstructured":"Evans, L.C.: Partial Differential Equations, vol. 19. American Mathematical Society, Providence (2010)"},{"issue":"2","key":"1114_CR90","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/s11118-011-9232-2","volume":"36","author":"ZM Balogh","year":"2012","unstructured":"Balogh, Z.M., Engulatov, A., Hunziker, L., Maasalo, O.E.: Functional inequalities and Hamilton\u2013Jacobi equations in geodesic spaces. Potential Anal. 36(2), 317\u2013337 (2012)","journal-title":"Potential Anal."},{"issue":"4","key":"1114_CR91","doi-asserted-by":"publisher","first-page":"713","DOI":"10.3934\/dcds.2007.17.713","volume":"17","author":"F Dragoni","year":"2007","unstructured":"Dragoni, F.: Metric Hopf\u2013Lax formula with semicontinuous data. Discrete Contin. Dyn. Syst. A 17(4), 713 (2007)","journal-title":"Discrete Contin. Dyn. Syst. A"},{"issue":"2","key":"1114_CR92","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1016\/j.jfa.2004.10.008","volume":"220","author":"D Azagra","year":"2005","unstructured":"Azagra, D., Ferrera, J., L\u00f3pez-Mesas, F.: Nonsmooth analysis and Hamilton\u2013Jacobi equations on Riemannian manifolds. J. Funct. Anal. 220(2), 304\u2013361 (2005)","journal-title":"J. Funct. Anal."},{"key":"1114_CR93","volume-title":"The Hamilton\u2013Jacobi Theory in the Calculus of Variations: Its Role in Mathematics and Physics","author":"H Rund","year":"1966","unstructured":"Rund, H.: The Hamilton\u2013Jacobi Theory in the Calculus of Variations: Its Role in Mathematics and Physics. Krieger Publishing Company, Malabar (1966)"},{"key":"1114_CR94","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1081\/PDE-120004897","volume":"27","author":"JJ Manfredi","year":"2002","unstructured":"Manfredi, J.J., Stroffolini, B.: A version of the Hopf\u2013Lax formula in the Heisenberg group. Commun. Partial Differ. Equ. 27, 1139\u20131159 (2002)","journal-title":"Commun. Partial Differ. Equ."},{"key":"1114_CR95","doi-asserted-by":"publisher","first-page":"47","DOI":"10.5201\/ipol.2019.227","volume":"9","author":"JM Mirebeau","year":"2019","unstructured":"Mirebeau, J.M., Portegies, J.: Hamiltonian fast marching: a numerical solver for anisotropic and non-holonomic eikonal PDEs. Image Process. On Line 9, 47\u201393 (2019)","journal-title":"Image Process. On Line"},{"issue":"4","key":"1114_CR96","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/TMI.2004.825627","volume":"23","author":"J Staal","year":"2004","unstructured":"Staal, J., Abr\u00e0moff, M.D., Niemeijer, M., Viergever, M.A., Van Ginneken, B.: Ridge-based vessel segmentation in color images of the retina. IEEE Trans. Med. Imaging 23(4), 501\u2013509 (2004)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"1114_CR97","unstructured":"Baweja, C.: RotNIST (2018). https:\/\/github.com\/ChaitanyaBaweja\/RotNIST"},{"key":"1114_CR98","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, pp. 8024\u20138035 (2019). www.ytorch.org"},{"key":"1114_CR99","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2014). arXiv preprint arXiv:1412.6980"},{"issue":"4","key":"1114_CR100","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"1114_CR101","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9982-5_1","volume-title":"Introduction to Smooth Manifolds. Graduate Texts in Mathematics","author":"J Lee","year":"2013","unstructured":"Lee, J.: Introduction to Smooth Manifolds. Graduate Texts in Mathematics, 2nd edn. Springer, Berlin (2013). https:\/\/doi.org\/10.1007\/978-1-4419-9982-5_1","edition":"2"}],"container-title":["Journal of Mathematical Imaging and Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-022-01114-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10851-022-01114-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-022-01114-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,29]],"date-time":"2023-01-29T00:21:57Z","timestamp":1674951717000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10851-022-01114-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,27]]},"references-count":101,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["1114"],"URL":"https:\/\/doi.org\/10.1007\/s10851-022-01114-x","relation":{},"ISSN":["0924-9907","1573-7683"],"issn-type":[{"value":"0924-9907","type":"print"},{"value":"1573-7683","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,27]]},"assertion":[{"value":"9 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}