{"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/local-binary-convolutional-neural-networks","title":"Local Binary Convolutional Neural Networks","arxiv_id":"1608.06049","date":"2016-08-22","proceeding":"CVPR 2017 7","authors":["Felix Juefei-Xu","Vishnu Naresh Boddeti","Marios Savvides"],"abstract":"We propose local binary convolution (LBC), an efficient alternative to\nconvolutional layers in standard convolutional neural networks (CNN). The\ndesign principles of LBC are motivated by local binary patterns (LBP). The LBC\nlayer comprises of a set of fixed sparse pre-defined binary convolutional\nfilters that are not updated during the training process, a non-linear\nactivation function and a set of learnable linear weights. The linear weights\ncombine the activated filter responses to approximate the corresponding\nactivated filter responses of a standard convolutional layer. The LBC layer\naffords significant parameter savings, 9x to 169x in the number of learnable\nparameters compared to a standard convolutional layer. Furthermore, the sparse\nand binary nature of the weights also results in up to 9x to 169x savings in\nmodel size compared to a standard convolutional layer. We demonstrate both\ntheoretically and experimentally that our local binary convolution layer is a\ngood approximation of a standard convolutional layer. Empirically, CNNs with\nLBC layers, called local binary convolutional neural networks (LBCNN), achieves\nperformance parity with regular CNNs on a range of visual datasets (MNIST,\nSVHN, CIFAR-10, and ImageNet) while enjoying significant computational savings.","url_abs":"http://arxiv.org/abs/1608.06049v2","url_pdf":"http://arxiv.org/pdf/1608.06049v2.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":"local-binary-convolutional-neural-networks","repo_url":"https://github.com/asaaditya8/LBCNN-keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"local-binary-convolutional-neural-networks","repo_url":"https://github.com/ericschaal/lbcnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"local-binary-convolutional-neural-networks","repo_url":"https://github.com/juefeix/lbcnn.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"local-binary-convolutional-neural-networks","repo_url":"https://github.com/juefeix/lbcnn.torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"local-binary-convolutional-neural-networks","repo_url":"https://github.com/juefeix/pnn.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"local-binary-convolutional-neural-networks","repo_url":"https://github.com/juefeix/pnn.pytorch.update","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-18","how":"tree_404+repo_404"}},{"paper_slug":"local-binary-convolutional-neural-networks","repo_url":"https://github.com/julianolm/Local-Binary-Convolutional-Neural-Network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.06049","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}