Papers › Iterative Normalization: Beyond Standardization towards Efficient Whitening

Iterative Normalization: Beyond Standardization towards Efficient Whitening

6 Apr 2019CVPR 2019 6arXiv:1904.03441archive 2025-07-28

Lei Huang, Yi Zhou, Fan Zhu, Li Liu, Ling Shao

Batch Normalization (BN) is ubiquitously employed for accelerating neural network training and improving the generalization capability by performing standardization within mini-batches. Decorrelated Batch Normalization (DBN) further boosts the above effectiveness by whitening. However, DBN relies heavily on either a large batch size, or eigen-decomposition that suffers from poor efficiency on GPUs. We propose Iterative Normalization (IterNorm), which employs Newton's iterations for much more efficient whitening, while simultaneously avoiding the eigen-decomposition. Furthermore, we develop a comprehensive study to show IterNorm has better trade-off between optimization and generalization, with theoretical and experimental support. To this end, we exclusively introduce Stochastic Normalization Disturbance (SND), which measures the inherent stochastic uncertainty of samples when applied to normalization operations. With the support of SND, we provide natural explanations to several phenomena from the perspective of optimization, e.g., why group-wise whitening of DBN generally outperforms full-whitening and why the accuracy of BN degenerates with reduced batch sizes. We demonstrate the consistently improved performance of IterNorm with extensive experiments on CIFAR-10 and ImageNet over BN and DBN.

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 (huangleiBuaa/IterNorm) was not harvested; the 14 samples below come from 2 community repositories.

Syntology 14 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 14 samples from 2 repositories, 12 ran (9 with no instrument failure; 3 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

huangleiBuaa/IterNorm officialmentioned in papermentioned on GitHubpytorchBSD-2-ClauseSyntology: not harvested report
XingangPan/Switchable-Whitening mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Switchable Whitening for Deep Representation Learning (arXiv:1904.09739; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
bhneo/DecorrelatedBN_tf mentioned on GitHubtfSyntology: not harvested report
bhneo/decorrelated_bn mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
huangleiBuaa/IterNorm-pytorch mentioned on GitHubpytorchBSD-2-ClauseSyntology: 13 samples, 11 ran (2 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
9ran
2unverified

Licence: 2 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

bhneo/decorrelated_bn community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
build_model_name vgg.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 14a171b5cbdb0117 · report fixture: signature params:MockParams/0/? · returned str · level recorded 2026-09-22
huangleiBuaa/IterNorm-pytorch community (archive-listed) 13 samples, 11 ran (2 instrument-failed) · 2 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
ImageNet/imagenet.py ran BSD-2-Clause (permissive) · a8ef2238d374d6cd · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
alexnet in 42 papers ImageNet/models/alexnet.py ran BSD-2-Clause (permissive) · ef99ba388dcdcf07 · report fixture: signature pretrained:bool/0/bool · returned AlexNet · level recorded 2026-09-24
conv3x3 in 1,376 papers ImageNet/models/resnet.py ran · our draft was wrong BSD-2-Clause (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
densenet121 in 43 papers ImageNet/models/densenet.py ran BSD-2-Clause (permissive) · f3db20d9541895a3 · report fixture: signature pretrained:bool/0/bool · returned DenseNet · level recorded 2026-09-24
densenet201 in 21 papers ImageNet/models/densenet.py ran BSD-2-Clause (permissive) · 4db46650afe56128 · report fixture: signature pretrained:bool/0/bool · returned DenseNet · level recorded 2026-09-24
make_layers in 155 papers ImageNet/models/vgg.py ran · our draft was wrong BSD-2-Clause (permissive) · ac62432dc5134b0d · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-24
squeezenet1_0 in 5 papers ImageNet/models/squeezenet.py ran BSD-2-Clause (permissive) · 82fb0599c9efd29e · report fixture: signature pretrained:bool/0/bool · returned SqueezeNet · level recorded 2026-09-24
squeezenet1_1 in 6 papers ImageNet/models/squeezenet.py ran BSD-2-Clause (permissive) · 0756b35ec8fe5483 · report fixture: signature pretrained:bool/0/bool · returned SqueezeNet · level recorded 2026-09-24
to_img in 8 papers cifar10/mnist.py ran BSD-2-Clause (permissive) · cacaa2915e934d81 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
vgg11 in 50 papers ImageNet/models/vgg.py ran BSD-2-Clause (permissive) · 3481975c041f9d95 · report fixture: signature pretrained:bool/0/bool · returned VGG · level recorded 2026-09-24
vgg11_bn in 40 papers ImageNet/models/vgg.py ran BSD-2-Clause (permissive) · 16c88c00e897cd0a · report fixture: signature pretrained:bool/0/bool · returned VGG · level recorded 2026-09-24
densenet169 in 42 papers ImageNet/models/densenet.py unverified BSD-2-Clause (permissive) · f8edcd0b3f2c5978 · report
inception_v3 in 16 papers ImageNet/models/inception.py unverified BSD-2-Clause (permissive) · e6e670a924cca390 · report

Tasks

Robust Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Robust Object Detection DWD IterNorm mPC [AP50] 23.4 #12 of 12 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

Batch NormalizationDecorrelated Batch NormalizationZCA Whitening

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