{"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/join-the-high-accuracy-club-on-imagenet-with","title":"Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket","arxiv_id":"2211.12933","date":"2022-11-23","proceeding":null,"authors":["Nianhui Guo","Joseph Bethge","Christoph Meinel","Haojin Yang"],"abstract":"Binary neural networks are the extreme case of network quantization, which has long been thought of as a potential edge machine learning solution. However, the significant accuracy gap to the full-precision counterparts restricts their creative potential for mobile applications. In this work, we revisit the potential of binary neural networks and focus on a compelling but unanswered problem: how can a binary neural network achieve the crucial accuracy level (e.g., 80%) on ILSVRC-2012 ImageNet? We achieve this goal by enhancing the optimization process from three complementary perspectives: (1) We design a novel binary architecture BNext based on a comprehensive study of binary architectures and their optimization process. (2) We propose a novel knowledge-distillation technique to alleviate the counter-intuitive overfitting problem observed when attempting to train extremely accurate binary models. (3) We analyze the data augmentation pipeline for binary networks and modernize it with up-to-date techniques from full-precision models. The evaluation results on ImageNet show that BNext, for the first time, pushes the binary model accuracy boundary to 80.57% and significantly outperforms all the existing binary networks. Code and trained models are available at: https://github.com/hpi-xnor/BNext.git.","url_abs":"https://arxiv.org/abs/2211.12933v3","url_pdf":"https://arxiv.org/pdf/2211.12933v3.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":"join-the-high-accuracy-club-on-imagenet-with","repo_url":"https://github.com/hpi-xnor/bnext","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.12933","atlas_url":"https://app.syntology.ai/?focus=2211.12933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12933"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/hpi-xnor/bnext","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"655597f0025b0542","entry":"accuracy","repo":"hpi-xnor/bnext","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"655597f0025b0542"}},{"code_sha256_prefix":"348e7ae7da0c6d25","entry":"adjust_temperature","repo":"hpi-xnor/bnext","repo_kind":"official","path":"src/train_assistant_group_amp.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/src/train_assistant_group_amp.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"348e7ae7da0c6d25"}},{"code_sha256_prefix":"fdd04ae393554ffa","entry":"build_transform","repo":"hpi-xnor/bnext","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fdd04ae393554ffa"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"hpi-xnor/bnext","repo_kind":"official","path":"src/bnext.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/src/bnext.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"71541b9507f823af","entry":"conv3x3","repo":"hpi-xnor/bnext","repo_kind":"official","path":"src/bnext.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/src/bnext.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71541b9507f823af"}},{"code_sha256_prefix":"23a8d2d1465d8757","entry":"adjust_sparse_rate","repo":"hpi-xnor/bnext","repo_kind":"official","path":"src/train_assistant_group_amp.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/src/train_assistant_group_amp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23a8d2d1465d8757"}},{"code_sha256_prefix":"f0b122e067f4f29b","entry":"conv1x1","repo":"hpi-xnor/bnext","repo_kind":"official","path":"src/birealnet.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/src/birealnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f0b122e067f4f29b"}},{"code_sha256_prefix":"b1748d851bc3ef77","entry":"otsu_loss","repo":"hpi-xnor/bnext","repo_kind":"official","path":"src/train_assistant_group_amp.py","file_url":"https://github.com/hpi-xnor/bnext/blob/HEAD/src/train_assistant_group_amp.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b1748d851bc3ef77"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}