Papers › On Feature Normalization and Data Augmentation

On Feature Normalization and Data Augmentation

25 Feb 2020CVPR 2021 1arXiv:2002.11102archive 2025-07-28

Boyi Li, Felix Wu, Ser-Nam Lim, Serge Belongie, Kilian Q. Weinberger

The moments (a.k.a., mean and standard deviation) of latent features are often removed as noise when training image recognition models, to increase stability and reduce training time. However, in the field of image generation, the moments play a much more central role. Studies have shown that the moments extracted from instance normalization and positional normalization can roughly capture style and shape information of an image. Instead of being discarded, these moments are instrumental to the generation process. In this paper we propose Moment Exchange, an implicit data augmentation method that encourages the model to utilize the moment information also for recognition models. Specifically, we replace the moments of the learned features of one training image by those of another, and also interpolate the target labels -- forcing the model to extract training signal from the moments in addition to the normalized features. As our approach is fast, operates entirely in feature space, and mixes different signals than prior methods, one can effectively combine it with existing augmentation approaches. We demonstrate its efficacy across several recognition benchmark data sets where it improves the generalization capability of highly competitive baseline networks with remarkable consistency.

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="2002.11102")

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: 3 ran · our draft was wrong.

By repository: official repository: 14 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Boyiliee/MoEx officialmentioned in papermentioned on GitHubpytorchBSD-3-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.

3ran · our draft was wrong
11unverified

Licence: 0 of the 14 samples are 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 Boyiliee/MoEx. “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.

conv1x1 Boyiliee/MoEx/ImageNet/moex_resnet.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · d9def42110729a85 · report
conv3x3 Boyiliee/MoEx/ImageNet/moex_resnet.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · 160bb14bd76201b4 · report
conv3x3 Boyiliee/MoEx/CIFAR/pyramidnet_moex.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · fac5364e2f53c6db · report
MLP Boyiliee/MoEx/ModelNet/pointnet2_classification_moex.py official repository unverified BSD-3-Clause (permissive) · b8bc16d9fb9a63e3 · report
fast_collate Boyiliee/MoEx/ImageNet/main_moex.py official repository unverified BSD-3-Clause (permissive) · 1795ac057ca3e793 · report
moex Boyiliee/MoEx/ImageNet/moex_resnet.py official repository unverified BSD-3-Clause (permissive) · 5f4567b0710fa9b5 · report
moex Boyiliee/MoEx/ModelNet/pointnet2_classification_moex.py official repository unverified BSD-3-Clause (permissive) · 22a17ae488f5df43 · report
rand_bbox Boyiliee/MoEx/CIFAR/train_moex.py official repository unverified BSD-3-Clause (permissive) · d34a085d71b8f4b5 · report
train Boyiliee/MoEx/ImageNet/main_moex.py official repository unverified BSD-3-Clause (permissive) · 750382b7eb3ffbc5 · report
train Boyiliee/MoEx/ImageNet/main_moex_cutmix.py official repository unverified BSD-3-Clause (permissive) · 78af1ef51a7861c5 · report
train Boyiliee/MoEx/ModelNet/pointnet2_classification_moex.py official repository unverified BSD-3-Clause (permissive) · c92643c0c22f35c2 · report
train Boyiliee/MoEx/CIFAR/train_moex.py official repository unverified BSD-3-Clause (permissive) · 0af00a0c1d3cde30 · report
validate Boyiliee/MoEx/ImageNet/main_moex.py official repository unverified BSD-3-Clause (permissive) · d3bd4edad0609d00 · report
validate Boyiliee/MoEx/CIFAR/train_moex.py official repository unverified BSD-3-Clause (permissive) · 4f145b01a69b877b · report

Tasks

Data AugmentationDomain GeneralizationImage ClassificationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A CutMix+MoEx (ResNet-50) Top-1 accuracy % 8.4 #32 of 39 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 BlockConvolutionCutMixGlobal 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