{"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/bi-real-net-enhancing-the-performance-of-1","title":"Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm","arxiv_id":"1808.00278","date":"2018-08-01","proceeding":"ECCV 2018 9","authors":["Zechun Liu","Baoyuan Wu","Wenhan Luo","Xin Yang","Wei Liu","Kwang-Ting Cheng"],"abstract":"In this work, we study the 1-bit convolutional neural networks (CNNs), of\nwhich both the weights and activations are binary. While being efficient, the\nclassification accuracy of the current 1-bit CNNs is much worse compared to\ntheir counterpart real-valued CNN models on the large-scale dataset, like\nImageNet. To minimize the performance gap between the 1-bit and real-valued CNN\nmodels, we propose a novel model, dubbed Bi-Real net, which connects the real\nactivations (after the 1-bit convolution and/or BatchNorm layer, before the\nsign function) to activations of the consecutive block, through an identity\nshortcut. Consequently, compared to the standard 1-bit CNN, the\nrepresentational capability of the Bi-Real net is significantly enhanced and\nthe additional cost on computation is negligible. Moreover, we develop a\nspecific training algorithm including three technical novelties for 1- bit\nCNNs. Firstly, we derive a tight approximation to the derivative of the\nnon-differentiable sign function with respect to activation. Secondly, we\npropose a magnitude-aware gradient with respect to the weight for updating the\nweight parameters. Thirdly, we pre-train the real-valued CNN model with a clip\nfunction, rather than the ReLU function, to better initialize the Bi-Real net.\nExperiments on ImageNet show that the Bi-Real net with the proposed training\nalgorithm achieves 56.4% and 62.2% top-1 accuracy with 18 layers and 34 layers,\nrespectively. Compared to the state-of-the-arts (e.g., XNOR Net), Bi-Real net\nachieves up to 10% higher top-1 accuracy with more memory saving and lower\ncomputational cost. Keywords: binary neural network, 1-bit CNNs,\n1-layer-per-block","url_abs":"http://arxiv.org/abs/1808.00278v5","url_pdf":"http://arxiv.org/pdf/1808.00278v5.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":"bi-real-net-enhancing-the-performance-of-1","repo_url":"https://github.com/liuzechun/Bi-Real-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"bi-real-net-enhancing-the-performance-of-1","repo_url":"https://github.com/JDAI-CV/dabnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"bi-real-net-enhancing-the-performance-of-1","repo_url":"https://github.com/sajaddarabi/BiRealNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bi-real-net-enhancing-the-performance-of-1","repo_url":"https://github.com/pminhtam/xnor_conv_pytorch_extension","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.00278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.00278"}},"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/pminhtam/xnor_conv_pytorch_extension","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sajaddarabi/BiRealNet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/liuzechun/Bi-Real-net","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JDAI-CV/dabnn","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"663e362628fdf530","entry":"birealnet18","repo":"liuzechun/Bi-Real-net","repo_kind":"official","path":"pytorch_implementation/BiReal18_34/birealnet.py","file_url":"https://github.com/liuzechun/Bi-Real-net/blob/HEAD/pytorch_implementation/BiReal18_34/birealnet.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"663e362628fdf530"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"d5cd7ffe2dc51b21","entry":"conv1x1","repo":"sajaddarabi/BiRealNet","repo_kind":"listed","path":"resnet_bireal.py","file_url":"https://github.com/sajaddarabi/BiRealNet/blob/HEAD/resnet_bireal.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5cd7ffe2dc51b21"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}