{"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/binarized-neural-networks-on-the-imagenet","title":"Binarized Neural Networks on the ImageNet Classification Task","arxiv_id":"1604.03058","date":"2016-04-11","proceeding":null,"authors":["Xundong Wu","Yong Wu","Yong Zhao"],"abstract":"We trained Binarized Neural Networks (BNNs) on the high resolution ImageNet\nILSVRC-2102 dataset classification task and achieved a good performance. With a\nmoderate size network of 13 layers, we obtained top-5 classification accuracy\nrate of 84.1 % on validation set through network distillation, much better than\nprevious published results of 73.2% on XNOR network and 69.1% on binarized\nGoogleNET. We expect networks of better performance can be obtained by\nfollowing our current strategies. We provide a detailed discussion and\npreliminary analysis on strategies used in the network training.","url_abs":"http://arxiv.org/abs/1604.03058v5","url_pdf":"http://arxiv.org/pdf/1604.03058v5.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":"binarized-neural-networks-on-the-imagenet","repo_url":"https://github.com/chencongchong/BNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}