Papers › Group Normalization

Group Normalization

22 Mar 2018ECCV 2018 9arXiv:1803.08494archive 2025-07-28

Yuxin Wu, Kaiming He

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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

Syntology 15 code samples harvested from 10 repositories linked to this paper: 7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 3 ran (2 with no instrument failure; 1 where Syntology's instrument failed); named in the paper: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 10 samples from 8 repositories, 4 ran (3 with no instrument failure; 1 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 5 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 7 samples that ran has no recorded date.

22 repositories listed; official and paper-mentioned ones first.

ppwwyyxx/GroupNorm-reproduce officialmentioned on GitHubtfApache-2.0Syntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
facebookresearch/detectron mentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Jarvis73/Group_Normalization mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
anzhao0503/group-normalization.pytorch mentioned on GitHubpytorchSyntology: not harvested report
blankWorld/GroupNorm-caffe mentioned on GitHubSyntology: not harvested report
changliu816/CV-paper-review mentioned on GitHubtfSyntology: not harvested report
chengyangfu/pytorch-groupnormalization mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
dmonterom/face_recognition_TF2 mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jiajunhua/facebookresearch-Detectron mentioned on GitHubcaffe2Syntology: 2 samples, 0 ran · 2 unverified report
ppwwyyxx/FRN-on-common-ImageNet-baseline mentioned on GitHubtfSyntology: not harvested report
pren1/Group-Normalization-Example mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
semskurto/APTOS mentioned on GitHubSyntology: not harvested report
taki0112/Group_Normalization-Tensorflow mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
taokong/group_normalization mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
titu1994/Keras-Group-Normalization mentioned on GitHubMITSyntology: not harvested report
vlievin/Unet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified) and Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-12 mindsporeSyntology: not harvested report
MindCode-4/code-7 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KPC-cF: Aspect-Based Sentiment Analysis via Implicit-Feature Alignment with Corpus Filtering (arXiv:2407.00342; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-12 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MCA-Bench: A Multimodal Benchmark for Evaluating CAPTCHA Robustness Against VLM-based Attacks (arXiv:2506.05982; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
nanzhaogang/contrib mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hyperspherical Consistency Regularization (arXiv:2206.00845; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

15 samples harvested: 7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 8 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.

1ran · our draft was wrong
1ran; the contract check could not run
5ran
8unverified

Licence: 5 of the 15 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 10 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. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

ppwwyyxx/GroupNorm-reproduce official repository 4 samples, 3 ran (1 instrument-failed) · 1 unverified
conv3x3 in 1,376 papers ImageNet-ResNet-PyTorch/resnet.py ran · our draft was wrong Apache-2.0 (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
resnet18 in 432 papers ImageNet-ResNet-PyTorch/resnet.py ran Apache-2.0 (permissive) · 3f579c5a3b36fa45 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
resnet34 in 148 papers ImageNet-ResNet-PyTorch/resnet.py ran Apache-2.0 (permissive) · e8dcd034178a8262 · report fixture: signature pretrained:bool/0/bool · returned ResNet · level recorded 2026-09-25
GroupNorm in 10 papers Cifar10-ResNet-TensorFlow/cifar10-resnet-gn.py unverified Apache-2.0 (permissive) · 27420f4cdbd391ae · report
facebookresearch/detectron named in the paper 1 sample, 0 ran · 1 unverified
bottleneck_gn_transformation detectron/modeling/ResNet.py unverified Apache-2.0 (permissive) · 0bd83b7f13c89101 · report
Jarvis73/Group_Normalization community (archive-listed) 1 sample, 0 ran · 1 unverified
GroupNormalization GroupNormalization.py unverified MIT (permissive) · bd97c13f0aaf126a · report
chengyangfu/pytorch-groupnormalization community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
group_norm in 17 papers group_norm.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 18d881658d555ef5 · report fixture: signature input:Tensor/4/float, group:int/0/int, running_mean:Tensor/1/float, running_var:Tensor/1/float, weight:Tensor/1/float, bias:Tensor/1/float, use_input_stats:bool/0/bool, momentum:float/0/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
dmonterom/face_recognition_TF2 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GroupNormalization resnet_groupNorm.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 443f07c373ca43d3 · report fixture: signature inputs:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
jiajunhua/facebookresearch-Detectron community (archive-listed) 2 samples, 0 ran · 2 unverified
basic_gn_stem detectron/modeling/ResNet.py unverified Apache-2.0 (permissive) · dd3d137d177c024b · report
get_group_gn in 5 papers detectron/modeling/ResNet.py unverified Apache-2.0 (permissive) · 8bc93accde20e097 · report
pren1/Group-Normalization-Example community (archive-listed) 1 sample, 0 ran · 1 unverified
GroupNorm in 10 papers Group_Normalization_example.py unverified no licence file found · pointer only · 8def41179ee858cb · report
taki0112/Group_Normalization-Tensorflow community (archive-listed) 1 sample, 0 ran · 1 unverified
group_norm in 17 papers norm.py unverified MIT (permissive) · f0a236a9978f0d8e · report
taokong/group_normalization community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GroupBatchnorm2d group_norm.py ran · metamorphic tier: deterministic no licence file found · pointer only · b1ab93188140a94f · report fixture: returned GroupBatchnorm2d · level recorded 2026-09-22
labmlai/annotated_deep_learning_paper_implementations community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
CIFAR10VGGModel labml_nn/normalization/group_norm/experiment.py ran MIT (permissive) · da29f85087b9fa45 · report fixture: returned CIFAR10VGGModel · level recorded 2026-09-22
Model in 227 papers labml_nn/normalization/group_norm/experiment.py unverified MIT (permissive) · e97f5db35a39c518 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

9 sibling assemblies for Group Normalization (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Group Normalization (graph method: Group Normalization). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. GroupBatchnorm2d entry · level 1 · ran · b1ab93188140a94f

harvested Assembly for Group Normalization (graph method: Group Normalization). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. group_norm entry · level 0 · unverified · f0a236a9978f0d8e

harvested Assembly for Group Normalization (graph method: Group Normalization). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. GroupNorm entry · level 0 · unverified · 8def41179ee858cb

harvested Assembly for Group Normalization (graph method: Group Normalization). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 9 siblings

  1. Model entry · level 0 · unverified · e97f5db35a39c518
  2. CIFAR10VGGModel helper · level 1 · ran · da29f85087b9fa45

harvested Assembly for Group Normalization (graph method: Group Normalization). 3 bricks; individually on a fixture: 0 ran · 3 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. basic_gn_stem entry · level 0 · unverified · dd3d137d177c024b
  2. get_group_gn helper · level 0 · unverified · 8bc93accde20e097
  3. AttrDict helper · level 0 · unverified · 5904b95e70b5177a

harvested Assembly for Group Normalization (graph method: Group Normalization). 3 bricks; individually on a fixture: 0 ran · 3 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. bottleneck_gn_transformation entry · level 0 · unverified · 0bd83b7f13c89101
  2. get_group_gn helper · level 0 · unverified · 8bc93accde20e097
  3. AttrDict helper · level 0 · unverified · 5904b95e70b5177a

harvested Assembly for Group Normalization (graph method: Group Normalization). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. GroupNormalization entry · level 0 · unverified · bd97c13f0aaf126a

harvested Assembly for Group Normalization (graph method: Group Normalization). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. GroupNormalization entry · level 1 · ran · 443f07c373ca43d3

harvested Assembly for Group Normalization (graph method: Group Normalization). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. group_norm entry · level 1 · ran; the contract check could not run (RAISES) · 18d881658d555ef5

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1803.08494") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ObjectObject DetectionVideo Classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival Mask R-CNN (ResNet-101-FPN, GroupNorm, long) AP50 62.8 #154 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-101-FPN, GroupNorm, long) AP75 46.2 #154 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-101-FPN, GroupNorm, long) box AP 42.3 #154 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GroupNorm, long) AP50 61.6 #173 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GroupNorm, long) AP75 44.4 #173 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GroupNorm, long) box AP 40.8 #173 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GroupNorm) AP50 61 #179 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GroupNorm) AP75 44 #179 of 220 Archive leaderboard report
Object Detection COCO minival Mask R-CNN (ResNet-50-FPN, GroupNorm) box AP 40.3 #179 of 220 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

Introduced by this paper: Group Normalization

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFPNFocal LossGlobal Average PoolingGroup NormalizationKaiming InitializationMask R-CNNMax PoolingRPNReLUResidual BlockResidual ConnectionRetinaNetRoIAlignSoftmax

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