{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/perforatedcnns-acceleration-through","title":"PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions","arxiv_id":"1504.08362","date":"2015-04-30","proceeding":"NeurIPS 2016 12","authors":["Michael Figurnov","Aijan Ibraimova","Dmitry Vetrov","Pushmeet Kohli"],"abstract":"We propose a novel approach to reduce the computational cost of evaluation of\nconvolutional neural networks, a factor that has hindered their deployment in\nlow-power devices such as mobile phones. Inspired by the loop perforation\ntechnique from source code optimization, we speed up the bottleneck\nconvolutional layers by skipping their evaluation in some of the spatial\npositions. We propose and analyze several strategies of choosing these\npositions. We demonstrate that perforation can accelerate modern convolutional\nnetworks such as AlexNet and VGG-16 by a factor of 2x - 4x. Additionally, we\nshow that perforation is complementary to the recently proposed acceleration\nmethod of Zhang et al.","url_abs":"http://arxiv.org/abs/1504.08362v4","url_pdf":"http://arxiv.org/pdf/1504.08362v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"perforatedcnns-acceleration-through","repo_url":"https://github.com/mfigurnov/perforated-cnn-caffe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"perforatedcnns-acceleration-through","repo_url":"https://github.com/mfigurnov/perforated-cnn-matconvnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1504.08362","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}