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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1904.03441")

Code

Syntology Ran 3 of 14 code samples harvested from 1 repository linked to this paper; 11 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran with no contract checked.

By repository: community (archive-listed): 13 samples from 1 repository, 2 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

huangleiBuaa/IterNorm officialmentioned in papermentioned on GitHubpytorchBSD-2-Clause report
XingangPan/Switchable-Whitening mentioned on GitHubpytorchMIT report
bhneo/DecorrelatedBN_tf mentioned on GitHubtf report
bhneo/decorrelated_bn mentioned on GitHubtf report
huangleiBuaa/IterNorm-pytorch mentioned on GitHubpytorchBSD-2-Clause 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

14 samples harvested; 3 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
1ran
11unverified

Licence: 1 of the 14 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from huangleiBuaa/IterNorm-pytorch. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

conv3x3 huangleiBuaa/IterNorm-pytorch/ImageNet/models/resnet.py community (archive-listed) ran · our draft was wrong BSD-2-Clause (permissive) · fac5364e2f53c6db · report
make_layers huangleiBuaa/IterNorm-pytorch/ImageNet/models/vgg.py community (archive-listed) ran BSD-2-Clause (permissive) · ac62432dc5134b0d · report
accuracy huangleiBuaa/IterNorm-pytorch/ImageNet/imagenet.py community (archive-listed) unverified BSD-2-Clause (permissive) · a8ef2238d374d6cd · report
alexnet huangleiBuaa/IterNorm-pytorch/ImageNet/models/alexnet.py community (archive-listed) unverified BSD-2-Clause (permissive) · ef99ba388dcdcf07 · report
densenet121 huangleiBuaa/IterNorm-pytorch/ImageNet/models/densenet.py community (archive-listed) unverified BSD-2-Clause (permissive) · f3db20d9541895a3 · report
densenet169 huangleiBuaa/IterNorm-pytorch/ImageNet/models/densenet.py community (archive-listed) unverified BSD-2-Clause (permissive) · f8edcd0b3f2c5978 · report
densenet201 huangleiBuaa/IterNorm-pytorch/ImageNet/models/densenet.py community (archive-listed) unverified BSD-2-Clause (permissive) · 4db46650afe56128 · report
inception_v3 huangleiBuaa/IterNorm-pytorch/ImageNet/models/inception.py community (archive-listed) unverified BSD-2-Clause (permissive) · e6e670a924cca390 · report
squeezenet1_0 huangleiBuaa/IterNorm-pytorch/ImageNet/models/squeezenet.py community (archive-listed) unverified BSD-2-Clause (permissive) · 82fb0599c9efd29e · report
squeezenet1_1 huangleiBuaa/IterNorm-pytorch/ImageNet/models/squeezenet.py community (archive-listed) unverified BSD-2-Clause (permissive) · 0756b35ec8fe5483 · report
to_img huangleiBuaa/IterNorm-pytorch/cifar10/mnist.py community (archive-listed) unverified BSD-2-Clause (permissive) · cacaa2915e934d81 · report
vgg11 huangleiBuaa/IterNorm-pytorch/ImageNet/models/vgg.py community (archive-listed) unverified BSD-2-Clause (permissive) · 3481975c041f9d95 · report
vgg11_bn huangleiBuaa/IterNorm-pytorch/ImageNet/models/vgg.py community (archive-listed) unverified BSD-2-Clause (permissive) · 16c88c00e897cd0a · report
build_model_name identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 14a171b5cbdb0117 · 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