{"id":6553,"date":"2011-12-11T19:19:46","date_gmt":"2011-12-11T17:19:46","guid":{"rendered":"http:\/\/hgpu.org\/?p=6553"},"modified":"2011-12-11T19:19:46","modified_gmt":"2011-12-11T17:19:46","slug":"self-supervised-clustering-for-codebook-construction-an-application-to-object-localization","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=6553","title":{"rendered":"Self-Supervised Clustering for Codebook Construction: An Application to Object Localization"},"content":{"rendered":"<p>Approaches to object localization based on codebooks do not exploit the dependencies between appearance and geometric information present in training data. This work addresses the problem of computing a codebook tailored to the task of localization by applying regularization based on geometric information. We present a novel method, the Regularized Combined Partitional-Agglomerative clustering, which extends the standard CPA method by adding extra knowledge to the clustering process to preserve as much geometric information as needed. Due to the time complexity of the methodology, we also present an implementation on the GPU using nVIDIA CUDA technology, speeding up the process with a factor over 100x.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Approaches to object localization based on codebooks do not exploit the dependencies between appearance and geometric information present in training data. This work addresses the problem of computing a codebook tailored to the task of localization by applying regularization based on geometric information. We present a novel method, the Regularized Combined Partitional-Agglomerative clustering, which extends [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,73,89,3],"tags":[468,1782,1791,14,20,220],"class_list":["post-6553","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-computer-vision","category-nvidia-cuda","category-paper","tag-clustering","tag-computer-science","tag-computer-vision","tag-cuda","tag-nvidia","tag-sift"],"views":2313,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/6553","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6553"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/6553\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6553"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6553"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6553"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}