Papers › Cross-Iteration Batch Normalization

Cross-Iteration Batch Normalization

13 Feb 2020CVPR 2021 1arXiv:2002.05712archive 2025-07-28

Zhuliang Yao, Yue Cao, Shuxin Zheng, Gao Huang, Stephen Lin

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 .

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (Howal/Cross-iterationBatchNorm) was not harvested; the 6 samples below come from 1 community repository.

Syntology 6 code samples harvested from 1 repository linked to this paper: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 6 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Howal/Cross-iterationBatchNorm officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report
hlld/cross-iteration-batch_normalization mentioned on GitHubtfApache-2.0Syntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
2unverified

Licence: 1 of the 6 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hlld/cross-iteration-batch_normalization. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

hlld/cross-iteration-batch_normalization community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
filter_regularization_variables utils.py ran Apache-2.0 (permissive) · 22863669fed87b1a · report fixture: signature variables:list/1/MockVariable, regularization_variable_regex:str/0/str · returned list · level recorded 2026-09-24
filter_trainable_variables utils.py ran Apache-2.0 (permissive) · 58c670dab5b13114 · report fixture: signature variables:list/1/MockVariable, frozen_variable_prefix:str/0/str · returned list · level recorded 2026-09-24
filter_variables utils.py ran Apache-2.0 (permissive) · 2d51886963260f5e · report fixture: signature variables:list/1/MockVariable, variable_regex:str/0/str, is_whitelist:bool/0/bool · returned list · level recorded 2026-09-24
load_CIFAR_batch cifar10.py ran Apache-2.0 (permissive) · 0387f93df835ab04 · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-24
load_CIFAR10 cifar10.py unverified Apache-2.0 (permissive) · 403a798c6fd52a08 · report
load_pickle in 115 papers cifar10.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · c0233f1d95c36390 · report

Tasks

Image ClassificationObject Detectionimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN, CBN) AP50 60.5 #197 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN, CBN) AP75 44.1 #197 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN, CBN) APL 38.5 #197 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN, CBN) APM 57.3 #197 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN, CBN) APS 35.8 #197 of 225 Archive leaderboard report
Object Detection COCO test-dev Mask R-CNN (ResNet-101-FPN, CBN) box mAP 40.1 #197 of 225 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections