{"id":17206,"date":"2017-04-30T22:45:54","date_gmt":"2017-04-30T19:45:54","guid":{"rendered":"https:\/\/hgpu.org\/?p=17206"},"modified":"2017-04-30T22:45:54","modified_gmt":"2017-04-30T19:45:54","slug":"icnet-for-real-time-semantic-segmentation-on-high-resolution-images","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=17206","title":{"rendered":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images"},"content":{"rendered":"<p>We focus on the challenging task of realtime semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an compressed-PSPNet-based image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion to quickly achieve high-quality segmentation. Our system yields realtime inference on a single GPU card with decent quality results evaluated on challenging Cityscapes dataset.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>We focus on the challenging task of realtime semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an compressed-PSPNet-based image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","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":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,73,89,3],"tags":[1782,1791,14,20,1767],"class_list":["post-17206","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-computer-vision","category-nvidia-cuda","category-paper","tag-computer-science","tag-computer-vision","tag-cuda","tag-nvidia","tag-nvidia-geforce-gtx-titan-x"],"views":2878,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/17206","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=17206"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/17206\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=17206"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=17206"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=17206"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}