{"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/batch-renormalization-towards-reducing","title":"Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models","arxiv_id":"1702.03275","date":"2017-02-10","proceeding":"NeurIPS 2017 12","authors":["Sergey Ioffe"],"abstract":"Batch Normalization is quite effective at accelerating and improving the\ntraining of deep models. However, its effectiveness diminishes when the\ntraining minibatches are small, or do not consist of independent samples. We\nhypothesize that this is due to the dependence of model layer inputs on all the\nexamples in the minibatch, and different activations being produced between\ntraining and inference. We propose Batch Renormalization, a simple and\neffective extension to ensure that the training and inference models generate\nthe same outputs that depend on individual examples rather than the entire\nminibatch. Models trained with Batch Renormalization perform substantially\nbetter than batchnorm when training with small or non-i.i.d. minibatches. At\nthe same time, Batch Renormalization retains the benefits of batchnorm such as\ninsensitivity to initialization and training efficiency.","url_abs":"http://arxiv.org/abs/1702.03275v2","url_pdf":"http://arxiv.org/pdf/1702.03275v2.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":"batch-renormalization-towards-reducing","repo_url":"https://github.com/dmonterom/face_recognition_TF2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"batch-renormalization-towards-reducing","repo_url":"https://github.com/eigenfoo/batch-renorm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"batch-renormalization-towards-reducing","repo_url":"https://github.com/ludvb/batchrenorm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"batch-renormalization-towards-reducing","repo_url":"https://github.com/prakhargoyal106/Batch_Renorm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"batch-renormalization-towards-reducing","repo_url":"https://github.com/seokhoonboo/caffe-boo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.03275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.03275"}},"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/dmonterom/face_recognition_TF2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/prakhargoyal106/Batch_Renorm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seokhoonboo/caffe-boo","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ludvb/batchrenorm","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eigenfoo/batch-renorm","reach":null}],"summary":{"ran_honours":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"4aad07e2e73786e5","entry":"get_dmax","repo":"eigenfoo/batch-renorm","repo_kind":"listed","path":"train_renorm.py","file_url":"https://github.com/eigenfoo/batch-renorm/blob/HEAD/train_renorm.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4aad07e2e73786e5"}},{"code_sha256_prefix":"06e05f7cb11610d4","entry":"get_rmax","repo":"eigenfoo/batch-renorm","repo_kind":"listed","path":"train_renorm.py","file_url":"https://github.com/eigenfoo/batch-renorm/blob/HEAD/train_renorm.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"06e05f7cb11610d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}