{"id":134288,"date":"2022-05-11T13:23:59","date_gmt":"2022-05-11T11:23:59","guid":{"rendered":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/"},"modified":"2022-05-11T13:23:59","modified_gmt":"2022-05-11T11:23:59","slug":"phd-defence-by-renfei-liu","status":"publish","type":"event","link":"https:\/\/uniavisen.dk\/en\/event\/phd-defence-by-renfei-liu\/","title":{"rendered":"PhD defence by Renfei Liu"},"content":{"rendered":"

Title<\/strong><\/h3>\n

Group and Pseudo-group Convolutional Neural Networks – Learning on Curved Spaces with the Application to DWI Segmentation<\/p>\n

Abstract<\/strong><\/h3>\n

This thesis is a compilation of a series of works generalizing convolutional neural networks to curved spaces in the application to DWI segmentation. We propose two types of generalization: generalizing to pseudo-group convolutions and full group convolutions. In the pseudo-group setup, we segment a DWI scan by classifying individual voxels, which are interpreted as spherical functions. In this case, the spherical functions are interpreted as functions on a general manifold. Thus, the function ns are locally lifted to tangent spaces, and convolutions are done in these tangent spaces. The lifting of the functions and the convolutions are done in a rotational way to take into account the different orientations of the functions caused by the path dependency of parallel transport on manifolds. This path dependency is then eliminated by summarizing all the rotations.
\nThe segmentation\/classification is then done by feeding the summarized features to a fully connected layer. This setup is not equivariant. In the full group setup, we segment a DWI scan by 1) looking at one individual voxel at a time 2) considering the neighboring grid of a voxel. In both cases, the underlying spaces of the functions are homogeneous spaces of the groups they are later lifted to, and full group convolutions are done in these groups. A summarization of the rotation symmetries is then performed, after which the summarized features are fed into a fully connected layer for segmentation\/classification purposes. This setup is equivariant. We design networks that take into account different types of symmetries of the data. By gradually incorporating more of these symmetries in the network, we provide a detailed study of the impact of these symmetries on the performance of the task.<\/p>\n

Supervisors<\/strong><\/p>\n

Principal Supervisor Kenny Erleben<\/p>\n

Co-Supervisor Sune Darkner<\/p>\n


\nAssessment Committee<\/strong><\/h3>\n

Professor Jon Sporring, Department of Computer Science<\/p>\n

Professor Aasa Feragen, DTU Compute<\/p>\n

Professor Remco Duits, Eindhoven University of Technology<\/p>\n

Moderator of defence<\/h3>\n

Mads Nielsen, Department of Computer Science<\/p>\n

For a digital copy of the thesis, please visit https:\/\/di.ku.dk\/english\/research\/phd\/<\/a><\/strong>.<\/p>\n","protected":false},"excerpt":{"rendered":"

Title Group and Pseudo-group Convolutional Neural Networks – Learning on Curved Spaces with the Application to DWI Segmentation Abstract This thesis is a compilation of a series of works generalizing convolutional neural networks to curved spaces in the application to DWI segmentation. We propose two types of generalization: generalizing to pseudo-group convolutions and full group […]<\/p>\n","protected":false},"author":0,"featured_media":134289,"template":"","class_list":["post-134288","event","type-event","status-publish","has-post-thumbnail","hentry","event_category-phd"],"acf":[],"yoast_head":"\nPhD defence by Renfei Liu<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"PhD defence by Renfei Liu\" \/>\n<meta property=\"og:description\" content=\"Title Group and Pseudo-group Convolutional Neural Networks – Learning on Curved Spaces with the Application to DWI Segmentation Abstract This thesis is a compilation of a series of works generalizing convolutional neural networks to curved spaces in the application to DWI segmentation. We propose two types of generalization: generalizing to pseudo-group convolutions and full group […]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/\" \/>\n<meta property=\"og:site_name\" content=\"University Post\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/uniavis\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@Uniavisen\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/\",\"url\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/\",\"name\":\"PhD defence by Renfei Liu\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/uniavisen.dk\\\/wp-content\\\/uploads\\\/2022\\\/05\\\/renfeiliuslideudentekst.jpg\",\"datePublished\":\"2022-05-11T11:23:59+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/#primaryimage\",\"url\":\"https:\\\/\\\/uniavisen.dk\\\/wp-content\\\/uploads\\\/2022\\\/05\\\/renfeiliuslideudentekst.jpg\",\"contentUrl\":\"https:\\\/\\\/uniavisen.dk\\\/wp-content\\\/uploads\\\/2022\\\/05\\\/renfeiliuslideudentekst.jpg\",\"width\":1100,\"height\":600},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/phd-defence-by-renfei-liu\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/uniavisen.dk\\\/en\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Events\",\"item\":\"https:\\\/\\\/uniavisen.dk\\\/event\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"PhD defence by Renfei Liu\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/uniavisen.dk\\\/#website\",\"url\":\"https:\\\/\\\/uniavisen.dk\\\/\",\"name\":\"University Post\",\"description\":\"Independent of management\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/uniavisen.dk\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"PhD defence by Renfei Liu","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/","og_locale":"en_US","og_type":"article","og_title":"PhD defence by Renfei Liu","og_description":"Title Group and Pseudo-group Convolutional Neural Networks – Learning on Curved Spaces with the Application to DWI Segmentation Abstract This thesis is a compilation of a series of works generalizing convolutional neural networks to curved spaces in the application to DWI segmentation. We propose two types of generalization: generalizing to pseudo-group convolutions and full group […]","og_url":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/","og_site_name":"University Post","article_publisher":"https:\/\/www.facebook.com\/uniavis","twitter_card":"summary_large_image","twitter_site":"@Uniavisen","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/","url":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/","name":"PhD defence by Renfei Liu","isPartOf":{"@id":"https:\/\/uniavisen.dk\/#website"},"primaryImageOfPage":{"@id":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/#primaryimage"},"image":{"@id":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/#primaryimage"},"thumbnailUrl":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst.jpg","datePublished":"2022-05-11T11:23:59+00:00","breadcrumb":{"@id":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/#primaryimage","url":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst.jpg","contentUrl":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst.jpg","width":1100,"height":600},{"@type":"BreadcrumbList","@id":"https:\/\/uniavisen.dk\/event\/phd-defence-by-renfei-liu\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/uniavisen.dk\/en\/"},{"@type":"ListItem","position":2,"name":"Events","item":"https:\/\/uniavisen.dk\/event\/"},{"@type":"ListItem","position":3,"name":"PhD defence by Renfei Liu"}]},{"@type":"WebSite","@id":"https:\/\/uniavisen.dk\/#website","url":"https:\/\/uniavisen.dk\/","name":"University Post","description":"Independent of management","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/uniavisen.dk\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"advancedCustomFields":{"event_category":{"term_id":143,"name":"Ph.d.-forsvar","slug":"phd","term_group":0,"term_taxonomy_id":143,"taxonomy":"event_category","description":"","parent":0,"count":408,"filter":"raw"},"start":"2022-05-24 09:00:00","add_end_time":true,"end":"2022-05-24 13:00:00","location":"Auditorium Lille UP 1, Universitetsparken 1, 2100 K\u00f8benhavn \u00d8","host_name":"Department of Computer Science ","ticket_link":"","event_is_free":false,"event_price":"Free ","event_poster":{"ID":134289,"id":134289,"title":"renfeiliuslideudentekst.jpg","filename":"renfeiliuslideudentekst.jpg","filesize":58820,"url":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst.jpg","link":"https:\/\/uniavisen.dk\/en\/event\/phd-defence-by-renfei-liu\/renfeiliuslideudentekst-jpg\/","alt":"","author":"0","description":"","caption":"","name":"renfeiliuslideudentekst-jpg","status":"inherit","uploaded_to":134288,"date":"2022-05-11 11:23:59","modified":"2022-05-11 11:23:59","menu_order":0,"mime_type":"image\/jpeg","type":"image","subtype":"jpeg","icon":"https:\/\/uniavisen.dk\/wp-includes\/images\/media\/default.png","width":1100,"height":600,"sizes":{"thumbnail":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst-150x150.jpg","thumbnail-width":150,"thumbnail-height":150,"medium":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst-480x262.jpg","medium-width":480,"medium-height":262,"medium_large":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst-768x419.jpg","medium_large-width":768,"medium_large-height":419,"large":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst.jpg","large-width":1100,"large-height":600,"1536x1536":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst.jpg","1536x1536-width":1100,"1536x1536-height":600,"2048x2048":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst.jpg","2048x2048-width":1100,"2048x2048-height":600,"featured-soft":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst-290x158.jpg","featured-soft-width":290,"featured-soft-height":158,"featured-hard":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst-290x180.jpg","featured-hard-width":290,"featured-hard-height":180,"narrow":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst-700x382.jpg","narrow-width":700,"narrow-height":382,"extended":"https:\/\/uniavisen.dk\/wp-content\/uploads\/2022\/05\/renfeiliuslideudentekst-990x540.jpg","extended-width":990,"extended-height":540}},"short_description":"On 24 May 2022, Renfei Liu will defend her PhD thesis titled 'Group and Pseudo-group Convolutional Neural Networks - Learning on Curved Spaces with the Application to DWI Segmentation'.","old_url":""},"_links":{"self":[{"href":"https:\/\/uniavisen.dk\/en\/wp-json\/wp\/v2\/events\/134288","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/uniavisen.dk\/en\/wp-json\/wp\/v2\/events"}],"about":[{"href":"https:\/\/uniavisen.dk\/en\/wp-json\/wp\/v2\/types\/event"}],"version-history":[{"count":0,"href":"https:\/\/uniavisen.dk\/en\/wp-json\/wp\/v2\/events\/134288\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/uniavisen.dk\/en\/wp-json\/wp\/v2\/media\/134289"}],"wp:attachment":[{"href":"https:\/\/uniavisen.dk\/en\/wp-json\/wp\/v2\/media?parent=134288"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}