{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T10:28:10Z","timestamp":1775730490931,"version":"3.50.1"},"reference-count":45,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T00:00:00Z","timestamp":1724284800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01\u2010CA246704"],"award-info":[{"award-number":["R01\u2010CA246704"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01\u2010CA268808"],"award-info":[{"award-number":["U01\u2010CA268808"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01 DK127384\u201002S1"],"award-info":[{"award-number":["U01 DK127384\u201002S1"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 CA240639\u201001"],"award-info":[{"award-number":["R01 CA240639\u201001"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:p>Capsule networks promise significant benefits over convolutional neural networks (CNN) by storing stronger internal representations and routing information based on the agreement between intermediate representations\u2019 projections. Despite this, their success has been limited to small\u2010scale classification datasets due to their computationally expensive nature. Though memory\u2010efficient, convolutional capsules impose geometric constraints that fundamentally limit the ability of capsules to model the pose\/deformation of objects. Further, they do not address the bigger memory concern of class capsules scaling up to bigger tasks such as detection or large\u2010scale classification. Herein, a new family of capsule networks, deformable capsules (<jats:italic>DeformCaps<\/jats:italic>), is introduced to address object detection problem in computer vision. Two new algorithms associated with our <jats:italic>DeformCaps<\/jats:italic>, a novel capsule structure (<jats:italic>SplitCaps<\/jats:italic>), and a novel dynamic routing algorithm (<jats:italic>SE\u2010Routing<\/jats:italic>), which balance computational efficiency with the need for modeling a large number of objects and classes, are proposed. This has never been achieved with capsule networks before. The proposed methods efficiently scale up to create the first\u2010ever capsule network for object detection in the literature. The proposed architecture is a one\u2010stage detection framework and it obtains results on microsoft common objects in context which are on par with state\u2010of\u2010the\u2010art one\u2010stage CNN\u2010based methods, while producing fewer false\u2010positive detection, generalizing to unusual poses\/viewpoints of objects.<\/jats:p>","DOI":"10.1002\/aisy.202400044","type":"journal-article","created":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T07:03:42Z","timestamp":1724310222000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deformable Capsules for Object Detection"],"prefix":"10.1002","volume":"6","author":[{"given":"Rodney","family":"LaLonde","sequence":"first","affiliation":[{"name":"Machine Learning Palantir Technologies  Washington DC 20007 USA"}]},{"given":"Naji","family":"Khosravan","sequence":"additional","affiliation":[{"name":"Machine Learning Applied Science Zillow  Seattle WA 98133 USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7379-6829","authenticated-orcid":false,"given":"Ulas","family":"Bagci","sequence":"additional","affiliation":[{"name":"Department of Radiology Northwestern University  Chicago IL 60611 USA"}]}],"member":"311","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_17"},{"key":"e_1_2_10_3_1","unstructured":"A.Punjabi J.Schmid A. K.Katsaggelos arXiv preprint arXiv:2001.109642020."},{"key":"e_1_2_10_4_1","first-page":"15486","volume-title":"Advances in Neural Information Processing Systems","author":"Kosiorek A.","year":"2019"},{"key":"e_1_2_10_5_1","first-page":"3856","volume-title":"Advances in Neural Information Processing Systems","author":"Sabour S.","year":"2017"},{"key":"e_1_2_10_6_1","unstructured":"M. A.Alcorn Q.Li Z.Gong C.Wang L.Mai W.\u2010S.Ku A.Nguyen inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2019 pp.4845\u20134854."},{"key":"e_1_2_10_7_1","unstructured":"G. E.Hinton S.Sabour N.Frosst inInter. Conf. on Learning Representations (ICLR) Montreal Canada April\u2010May2018."},{"key":"e_1_2_10_8_1","unstructured":"R.LaLonde U.Bagci inMedical Imaging with Deep Learning (MIDL) Amsterdam Netherland July2018."},{"key":"e_1_2_10_9_1","unstructured":"R.LaLonde P.Kandel C.Spampinato M. B.Wallace U.Bagci inInter. Symp. on Biomedical Imaging (ISBI) IEEE Piscataway NJ2020."},{"key":"e_1_2_10_10_1","first-page":"7610","volume-title":"Advances in Neural Information Processing Systems","author":"Duarte K.","year":"2018"},{"key":"e_1_2_10_11_1","unstructured":"J.Dai H.Qi Y.Xiong Y.Li G.Zhang H.Hu Y.Wei inThe IEEE Inter. Conf. on Computer Vision (ICCV) IEEE Piscataway NJ2017 pp.764\u2013773."},{"key":"e_1_2_10_12_1","unstructured":"X.Zhou D.Wang P.Kr\u00e4henb\u00fchl arXiv preprint arXiv:1904.078502019."},{"key":"e_1_2_10_13_1","unstructured":"Y.\u2010H. H.Tsai N.Srivastava H.Goh R.Salakhutdinov inInter. Conf. on Learning Representations (ICLR) Addis Ababa Ethiopia April2020."},{"key":"e_1_2_10_14_1","unstructured":"F.Yu D.Wang E.Shelhamer T.Darrell inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition IEEE Piscataway NJ2018 pp.2403\u20132412."},{"key":"e_1_2_10_15_1","unstructured":"K.He G.Gkioxari P.Doll\u00e1r R.Girshick inProc. of the IEEE Inter. Conf. on Computer Vision IEEE Piscataway NJ2017 pp.2961\u20132969."},{"key":"e_1_2_10_16_1","doi-asserted-by":"crossref","unstructured":"F.Milletari N.Navab S.\u2010A.Ahmadi in2016 Fourth Inter. Conf. on 3D Vision (3DV) IEEE Piscataway NJ2016 pp.565\u2013571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_10_17_1","unstructured":"H.Law J.Deng inProc. of the European Conf. on Computer Vision (ECCV) Munich Germany September2018 pp.734\u2013750."},{"key":"e_1_2_10_18_1","unstructured":"T.\u2010Y.Lin P.Goyal R.Girshick K.He P.Doll\u00e1r inThe IEEE Inter. Conf. on Computer Vision (ICCV) IEEE Piscataway NJ2017 pp.2980\u20132988."},{"key":"e_1_2_10_19_1","unstructured":"J.Hu L.Shen G.Sun inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition IEEE Piscataway NJ2018 pp.7132\u20137141."},{"key":"e_1_2_10_20_1","unstructured":"I.Paik T.Kwak I.Kim arXiv preprint arXiv:1907.133272019."},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1539-6924.1999.tb00399.x"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704873"},{"key":"e_1_2_10_23_1","doi-asserted-by":"crossref","unstructured":"T.\u2010Y.Lin M.Maire S.Belongie J.Hays P.Perona D.Ramanan P.Doll\u00e1r C. L.Zitnick inProc. of the European Conf. on Computer Vision (ECCV).Springer Berlin2014 pp.740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_2_10_24_1","unstructured":"D. P.Kingma J.Ba inInter. Conf. on Learning Representations (ICLR) Banff AB Canada April2014."},{"key":"e_1_2_10_25_1","doi-asserted-by":"crossref","unstructured":"G. E.Hinton A.Krizhevsky S. D.Wang inInter. Conf. on Artificial Neural Networks Springer Berlin2011 pp.44\u201351.","DOI":"10.1007\/978-3-642-21735-7_6"},{"key":"e_1_2_10_26_1","unstructured":"F. D. S.Ribeiro K.Duarte M.Everett G.Leontidis M.Shah arXiv preprint arXiv:2206.026642022."},{"key":"e_1_2_10_27_1","unstructured":"K.Duarte Y. S.Rawat M.Shah inThe IEEE Inter. Conf. on Computer Vision (ICCV) IEEE Piscataway NJ2019."},{"key":"e_1_2_10_28_1","doi-asserted-by":"crossref","unstructured":"Y.Zhao T.Birdal H.Deng F.Tombari inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition IEEE Piscataway NJ2019 pp.1009\u20131018.","DOI":"10.1109\/CVPR.2019.00110"},{"key":"e_1_2_10_29_1","unstructured":"R.LaLonde D.Torigian U.Bagci inInter. Conf. on Medical Image Computing and Computer\u2010Assisted Intervention (MICCAI) Springer Berlin2020."},{"key":"e_1_2_10_30_1","unstructured":"W.Zhao J.Ye M.Yang Z.Lei S.Zhang Z.Zhao arXiv preprint arXiv:1804.005382018."},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"Y.Wang A.Sun J.Han Y.Liu X.Zhu inProc. of the World Wide Web Conf. 2018 pp.1165\u20131174.","DOI":"10.1145\/3178876.3186015"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.32604\/jai.2019.05817"},{"key":"e_1_2_10_33_1","doi-asserted-by":"crossref","unstructured":"R.Girshick J.Donahue T.Darrell J.Malik inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2014 pp.580\u2013587.","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_2_10_34_1","doi-asserted-by":"crossref","unstructured":"R.Girshick inThe IEEE Inter. Conf. on Computer Vision (ICCV) IEEE Piscataway NJ2015 pp.1440\u20131448.","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_10_35_1","first-page":"91","volume-title":"Advances in Neural Information Processing Systems","author":"Ren S.","year":"2015"},{"key":"e_1_2_10_36_1","doi-asserted-by":"crossref","unstructured":"J.Redmon S.Divvala R.Girshick A.Farhadi inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2016 pp.779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_10_37_1","unstructured":"J.Redmon A.Farhadi inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2017 pp.7263\u20137271."},{"key":"e_1_2_10_38_1","unstructured":"J.Redmon A.Farhadi arXiv preprint arXiv:1804.027672018."},{"key":"e_1_2_10_39_1","doi-asserted-by":"crossref","unstructured":"W.Liu D.Anguelov D.Erhan C.Szegedy S.Reed C.\u2010Y.Fu A. C.Berg inProc. of the European Conf. on Computer Vision (ECCV) Springer Berlin2016 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_2_10_40_1","first-page":"1","author":"Chen Z.","year":"2020","journal-title":"Int. J. Comput. Vis."},{"key":"e_1_2_10_41_1","unstructured":"X.Zhou J.Zhuo P.Krahenbuhl inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2019 pp.850\u2013859."},{"key":"e_1_2_10_42_1","unstructured":"X.Zhu H.Hu S.Lin J.Dai inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) IEEE Piscataway NJ2019 pp.9308\u20139316."},{"key":"e_1_2_10_43_1","first-page":"9310","volume-title":"Advances in Neural Information Processing Systems","author":"Singh B.","year":"2018"},{"key":"e_1_2_10_44_1","unstructured":"S.Liu L.Qi H.Qin J.Shi J.Jia inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition IEEE Piscataway NJ2018 pp.8759\u20138768."},{"key":"e_1_2_10_45_1","unstructured":"Y.Li Y.Chen N.Wang Z.Zhang inProc. of the IEEE Inter. Conf. on Computer Vision IEEE Piscataway NJ2019 pp.6054\u20136063."},{"key":"e_1_2_10_46_1","unstructured":"S.Zhang L.Wen X.Bian Z.Lei S. Z.Li inProc. of the IEEE Conf. on Computer Vision and Pattern Recognition IEEE Piscataway NJ2018 pp.4203\u20134212."}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202400044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:17Z","timestamp":1759881617000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202400044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,22]]},"references-count":45,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["10.1002\/aisy.202400044"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202400044","archive":["Portico"],"relation":{},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"value":"2640-4567","type":"print"},{"value":"2640-4567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,22]]},"assertion":[{"value":"2024-01-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2400044"}}