We investigate the gains in precision and speed, that can be obtained by using Convolutional Networks (ConvNets) for on-the-fly retrieval – where classifiers are learnt at run time for a textual query from downloaded images, and used to rank large image or video datasets.<\/p>\n
We make three contributions: (i) we present an evaluation of state-of-the-art image representations for object category retrieval over standard benchmark datasets containing 1M+ images; (ii) we show that ConvNets can be used to obtain features which are incredibly performant, and yet much lower dimensional than previous state-of-the-art image representations, and that their dimensionality can be reduced further without loss in performance by compression using product quantization or binarization. Consequently, features with the state-of-the-art performance on large-scale datasets of millions of images can fit in the memory of even a commodity GPU card; (iii) we show that an SVM classifier can be learnt within a ConvNet framework on a GPU in parallel with downloading the new training images, allowing for a continuous refinement of the model as more images become available, and simultaneous training and ranking. The outcome is an on-the-fly system that significantly outperforms its predecessors in terms of: precision of retrieval, memory requirements, and speed facilitating accurate on-the-fly learning and ranking in under a second on a single GPU.<\/p>\n","protected":false},"excerpt":{"rendered":"
We investigate the gains in precision and speed, that can be obtained by using Convolutional Networks (ConvNets) for on-the-fly retrieval – where classifiers are learnt at run time for a textual query from downloaded images, and used to rank large image or video datasets. We make three contributions: (i) we present an evaluation of state-of-the-art […]<\/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":[1782,1791,14,1025,608,20,1470,469],"class_list":["post-12519","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-machine-learning","tag-neural-and-evolutionary-computing","tag-nvidia","tag-nvidia-geforce-gtx-titan","tag-pattern-recognition"],"views":1907,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/12519","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=12519"}],"version-history":[{"count":1,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/12519\/revisions"}],"predecessor-version":[{"id":12525,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/12519\/revisions\/12525"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=12519"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=12519"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=12519"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}