{"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/cross-iteration-batch-normalization","title":"Cross-Iteration Batch Normalization","arxiv_id":"2002.05712","date":"2020-02-13","proceeding":"CVPR 2021 1","authors":["Zhuliang Yao","Yue Cao","Shuxin Zheng","Gao Huang","Stephen Lin"],"abstract":"A well-known issue of Batch Normalization is its significantly reduced effectiveness in the case of small mini-batch sizes. When a mini-batch contains few examples, the statistics upon which the normalization is defined cannot be reliably estimated from it during a training iteration. To address this problem, we present Cross-Iteration Batch Normalization (CBN), in which examples from multiple recent iterations are jointly utilized to enhance estimation quality. A challenge of computing statistics over multiple iterations is that the network activations from different iterations are not comparable to each other due to changes in network weights. We thus compensate for the network weight changes via a proposed technique based on Taylor polynomials, so that the statistics can be accurately estimated and batch normalization can be effectively applied. On object detection and image classification with small mini-batch sizes, CBN is found to outperform the original batch normalization and a direct calculation of statistics over previous iterations without the proposed compensation technique. Code is available at https://github.com/Howal/Cross-iterationBatchNorm .","url_abs":"https://arxiv.org/abs/2002.05712v3","url_pdf":"https://arxiv.org/pdf/2002.05712v3.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":"cross-iteration-batch-normalization","repo_url":"https://github.com/Howal/Cross-iterationBatchNorm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cross-iteration-batch-normalization","repo_url":"https://github.com/hlld/cross-iteration-batch_normalization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"Mask R-CNN (ResNet-101-FPN, CBN)","rank_in_archive_order":197,"of":225,"metrics":{"AP50":"60.5","AP75":"44.1","APL":"38.5","APM":"57.3","APS":"35.8","box mAP":"40.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.05712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.05712"}},"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/Howal/Cross-iterationBatchNorm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hlld/cross-iteration-batch_normalization","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"22863669fed87b1a","entry":"filter_regularization_variables","repo":"hlld/cross-iteration-batch_normalization","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/hlld/cross-iteration-batch_normalization/blob/HEAD/utils.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":"22863669fed87b1a"}},{"code_sha256_prefix":"58c670dab5b13114","entry":"filter_trainable_variables","repo":"hlld/cross-iteration-batch_normalization","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/hlld/cross-iteration-batch_normalization/blob/HEAD/utils.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":"58c670dab5b13114"}},{"code_sha256_prefix":"2d51886963260f5e","entry":"filter_variables","repo":"hlld/cross-iteration-batch_normalization","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/hlld/cross-iteration-batch_normalization/blob/HEAD/utils.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":"2d51886963260f5e"}},{"code_sha256_prefix":"403a798c6fd52a08","entry":"load_CIFAR10","repo":"hlld/cross-iteration-batch_normalization","repo_kind":"listed","path":"cifar10.py","file_url":"https://github.com/hlld/cross-iteration-batch_normalization/blob/HEAD/cifar10.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":"403a798c6fd52a08"}},{"code_sha256_prefix":"0387f93df835ab04","entry":"load_CIFAR_batch","repo":"hlld/cross-iteration-batch_normalization","repo_kind":"listed","path":"cifar10.py","file_url":"https://github.com/hlld/cross-iteration-batch_normalization/blob/HEAD/cifar10.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":"0387f93df835ab04"}},{"code_sha256_prefix":"c0233f1d95c36390","entry":"load_pickle","repo":"hlld/cross-iteration-batch_normalization","repo_kind":"listed","path":"cifar10.py","file_url":"https://github.com/hlld/cross-iteration-batch_normalization/blob/HEAD/cifar10.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":"c0233f1d95c36390"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}