{"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/binary-ensemble-neural-network-more-bits-per","title":"Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?","arxiv_id":"1806.07550","date":"2018-06-20","proceeding":"CVPR 2019 6","authors":["Shilin Zhu","Xin Dong","Hao Su"],"abstract":"Binary neural networks (BNN) have been studied extensively since they run\ndramatically faster at lower memory and power consumption than floating-point\nnetworks, thanks to the efficiency of bit operations. However, contemporary\nBNNs whose weights and activations are both single bits suffer from severe\naccuracy degradation. To understand why, we investigate the representation\nability, speed and bias/variance of BNNs through extensive experiments. We\nconclude that the error of BNNs is predominantly caused by the intrinsic\ninstability (training time) and non-robustness (train & test time). Inspired by\nthis investigation, we propose the Binary Ensemble Neural Network (BENN) which\nleverages ensemble methods to improve the performance of BNNs with limited\nefficiency cost. While ensemble techniques have been broadly believed to be\nonly marginally helpful for strong classifiers such as deep neural networks,\nour analyses and experiments show that they are naturally a perfect fit to\nboost BNNs. We find that our BENN, which is faster and much more robust than\nstate-of-the-art binary networks, can even surpass the accuracy of the\nfull-precision floating number network with the same architecture.","url_abs":"http://arxiv.org/abs/1806.07550v2","url_pdf":"http://arxiv.org/pdf/1806.07550v2.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":"binary-ensemble-neural-network-more-bits-per","repo_url":"https://github.com/XinDongol/BENN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.07550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07550"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XinDongol/BENN-PyTorch","reach":null}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"3091e428d13ac1dd","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3091e428d13ac1dd"}},{"code_sha256_prefix":"fb56731c1050144a","entry":"get_error_output","repo":"XinDongol/BENN-PyTorch","repo_kind":"listed","path":"cifar/AB/bagging/main_bagging_AB.py","file_url":"https://github.com/XinDongol/BENN-PyTorch/blob/HEAD/cifar/AB/bagging/main_bagging_AB.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb56731c1050144a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}