{"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/distribution-aware-binarization-of-neural","title":"Distribution-Aware Binarization of Neural Networks for Sketch Recognition","arxiv_id":"1804.02941","date":"2018-04-09","proceeding":null,"authors":["Ameya Prabhu","Vishal Batchu","Sri Aurobindo Munagala","Rohit Gajawada","Anoop Namboodiri"],"abstract":"Deep neural networks are highly effective at a range of computational tasks.\nHowever, they tend to be computationally expensive, especially in\nvision-related problems, and also have large memory requirements. One of the\nmost effective methods to achieve significant improvements in\ncomputational/spatial efficiency is to binarize the weights and activations in\na network. However, naive binarization results in accuracy drops when applied\nto networks for most tasks. In this work, we present a highly generalized,\ndistribution-aware approach to binarizing deep networks that allows us to\nretain the advantages of a binarized network, while reducing accuracy drops. We\nalso develop efficient implementations for our proposed approach across\ndifferent architectures. We present a theoretical analysis of the technique to\nshow the effective representational power of the resulting layers, and explore\nthe forms of data they model best. Experiments on popular datasets show that\nour technique offers better accuracies than naive binarization, while retaining\nthe same benefits that binarization provides - with respect to run-time\ncompression, reduction of computational costs, and power consumption.","url_abs":"http://arxiv.org/abs/1804.02941v1","url_pdf":"http://arxiv.org/pdf/1804.02941v1.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":"distribution-aware-binarization-of-neural","repo_url":"https://github.com/erilyth/DistributionAwareBinarizedNetworks-WACV18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"binarization","task_name":"Binarization"},{"task_slug":"sketch-recognition","task_name":"Sketch Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}