{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:29:08Z","timestamp":1787326148384,"version":"build-2736575974"},"reference-count":46,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"name":"German Federal Ministry of Education and Research","award":["05M2020 (DAnoBi)"],"award-info":[{"award-number":["05M2020 (DAnoBi)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Imaging Sci."],"published-print":{"date-parts":[[2024,6,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>Scattering networks yield powerful and robust hierarchical image descriptors which do not require lengthy training and which work well with very few training data. However, they rely on sampling the scale dimension. Hence, they become sensitive to scale variations and are unable to generalize to unseen scales. In this work, we define an alternative feature representation based on the Riesz transform. We detail and analyze the mathematical foundations behind this representation. In particular, it inherits scale equivariance from the Riesz transform and completely avoids sampling of the scale dimension. Additionally, the number of features in the representation is reduced by a factor four compared to scattering networks. Nevertheless, our representation performs comparably well for texture classification with an interesting addition: scale equivariance. Our method yields very good performance when dealing with scales outside of those covered by the training dataset. The usefulness of the equivariance property is demonstrated on the digit classification task, where accuracy remains stable even for scales four times larger than the one chosen for training. As a second example, we consider classification of textures. Finally, we show how this representation can be used to build hybrid deep learning methods that are more stable to scale variations than standard deep networks.<\/jats:p>","DOI":"10.1137\/23m1584836","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T17:04:51Z","timestamp":1718903091000},"page":"1284-1313","source":"Crossref","is-referenced-by-count":3,"title":["Riesz Feature Representation: Scale Equivariant Scattering Network for Classification Tasks"],"prefix":"10.1137","volume":"17","author":[{"given":"Tin","family":"Barisin","sequence":"first","affiliation":[{"name":"RPTU Kaiserslautern-Landau, Kaiserslautern, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesus","family":"Angulo","sequence":"additional","affiliation":[{"name":"Center for Mathematical Morphology MINES Paris, PSL Research University, Fontainebleau, France."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katja","family":"Schladitz","sequence":"additional","affiliation":[{"name":"Fraunhofer-Institut f\u00fcr Techno- und Wirtschaftsmathematik (ITWM), Kaiserslautern, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Redenbach","sequence":"additional","affiliation":[{"name":"RPTU Kaiserslautern-Landau, Kaiserslautern, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"ref1","first-page":"1","volume":"21","author":"Andreux M.","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-024-01171-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1023\/B:JMIV.0000026557.50965.09"},{"key":"ref4","unstructured":"J. Bruna, Scattering Representations for Recognition, Doctoral dissertation, Ecole Polytechnique X, 2013."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995635"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.230"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14495\/jsiaml.15.21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168136"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802977"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5566\/ias.1964"},{"key":"ref11","volume-title":"Low-Level Image Processing with the Structure Multivector","author":"Felsberg M.","year":"2002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/78.969520"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1023\/B:JMIV.0000026554.79537.35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/34.93808"},{"key":"ref15","author":"Fritz M.","year":"2004","journal-title":"The kth-Tips Database"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00566"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1142\/S0219691314500271"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"E. Hayman, B. Caputo, M. Fritz, and J.O. Eklundh, On the significance of real-world conditions for material classification, in European Conference on Computer Vision, Springer, 2004, pp. 253\u2013266.","DOI":"10.1007\/978-3-540-24673-2_21"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2036713"},{"key":"ref20","doi-asserted-by":"crossref","unstructured":"Y. Jansson and T. Lindeberg, Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges, in 25th IEEE International Conference on Pattern Recognition (ICPR), 2021, pp. 1181\u20131188.","DOI":"10.1109\/ICPR48806.2021.9413276"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-022-01082-2"},{"key":"ref22","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma D.","year":"2015"},{"key":"ref23","unstructured":"A. Krizhevsky, V. Nair, and G. Hinton, Cifar-10 (canadian institute for advanced research) 5, 2010, 1, https:\/\/www.cs.toronto.edu\/\u223ckriz\/cifar.html."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1080\/757582976"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008045108935"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-014-0541-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-019-00915-x"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-021-01057-9"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"D. G. Lowe, Object recognition from local scale-invariant features, in Proceedings of the Seventh IEEE International Conference on Computer Vision, Vol. 2, 1999, pp. 1150\u20131157.","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21413"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2015.0203"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2009.2023397"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.599"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298904"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2855738"},{"key":"ref37","first-page":"2825","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s00006-022-01237-9"},{"key":"ref39","unstructured":"M. Sangalli, S. Blusseau, S. Velasco-Forero, and J. Angulo, Scale equivariant u-net, in 33rd British Machine Vision Conference, 2022."},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.163"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2027628"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2038832"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-013-0738-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2776228"},{"key":"ref45","first-page":"130","volume-title":"Geometric Deep Learning in Medical Image Analysis","author":"Yang Y.","year":"2022"},{"key":"ref46","doi-asserted-by":"crossref","unstructured":"S. Zagoruyko and N. Komodakis, Wide residual networks, in British Machine Vision Conference, British Machine Vision Association, 2016.","DOI":"10.5244\/C.30.87"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/23M1584836","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:27:30Z","timestamp":1787322450000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/23M1584836"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,20]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6,30]]}},"alternative-id":["10.1137\/23M1584836"],"URL":"https:\/\/doi.org\/10.1137\/23m1584836","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,20]]}}}