Papers › Mean teachers are better role models: Weight-averaged consistency targets improve...

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

6 Mar 2017NeurIPS 2017 12arXiv:1703.01780archive 2025-07-28

Antti Tarvainen, Harri Valpola

The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change only once per epoch, Temporal Ensembling becomes unwieldy when learning large datasets. To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions. As an additional benefit, Mean Teacher improves test accuracy and enables training with fewer labels than Temporal Ensembling. Without changing the network architecture, Mean Teacher achieves an error rate of 4.35% on SVHN with 250 labels, outperforming Temporal Ensembling trained with 1000 labels. We also show that a good network architecture is crucial to performance. Combining Mean Teacher and Residual Networks, we improve the state of the art on CIFAR-10 with 4000 labels from 10.55% to 6.28%, and on ImageNet 2012 with 10% of the labels from 35.24% to 9.11%.

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 (CuriousAI/mean-teacher) was not harvested; the 3 samples below come from 1 community repository, and 3 more are identical to code Syntology harvested from another paper's repository.

Syntology 6 code samples: 3 from 1 repository linked to this paper, 3 identical to code harvested from another paper's repository. Across all 6: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); 3 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.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

CuriousAI/mean-teacher officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: not harvested report
INK-USC/DualRE mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Dual Retrieval Module for Semi-supervised Relation Extraction (arXiv:1902.07814; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Lan1991Xu/ONE_NeurIPS2018 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Knowledge Distillation by On-the-Fly Native Ensemble (arXiv:1806.04606; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
ZHKKKe/PixelSSL mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-Supervised Semantic Segmentation with Cross-Consistency Training (arXiv:2003.09005; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
benathi/fastswa-semi-sup mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Ensembling for Semi-Supervised Learning (arXiv:1610.02242; that paper's own run record: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
liuwei16/ALFNet mentioned on GitHubtfSyntology: not harvested report
shunk031/chainer-MeanTeachers mentioned on GitHubSyntology: not harvested report
sud0301/semisup-semseg mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 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

6 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 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.

2ran · honoured contract
4ran; the contract check could not run

Licence: 6 of the 6 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 sud0301/semisup-semseg. 3 samples are listed last, in a group without a repository. “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.

sud0301/semisup-semseg community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
train_mlmt.py ran; the contract check could not run (RAISES) no licence file found · pointer only · fddaf151399b812a · report fixture: returned tuple · level recorded 2026-09-22
cosine_loss in 10 papers train_mlmt.py ran; the contract check could not run (RAISES) no licence file found · pointer only · f9bfc647f202a8e0 · report fixture: returned Tensor · level recorded 2026-09-22
one_hot in 150 papers
census: 18 implementations from 25 papers, 10 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 4 of 6, arg 1: rank 3, kind float, dtype float32
train_s4GAN.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 3d0fa6038b78822c · report fixture: signature label:Tensor/3/float · returned Tensor · level recorded 2026-09-22
Repository not located 3 samples, 3 ran (1 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
color_map in 15 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · fcbd501f30a007d4 · report fixture: signature N:int/0/int, normalized:bool/0/bool · returned ndarray · level recorded 2026-09-22
get_label_vector in 6 papers repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted licence of this copy not recorded · 799a094d0124a46c · report fixture: signature target:ndarray/1/int, nclass:int/0/int · returned ndarray · level recorded 2026-09-22
lr_poly in 25 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · b3b7c1c716f4ca66 · report fixture: signature base_lr:float/0/float, iter:int/0/int, max_iter:int/0/int, power:float/0/float · returned float · level recorded 2026-09-22

Tasks

Semi-Supervised Image ClassificationSemi-Supervised RGBD Semantic SegmentationSemi-Supervised Semantic SegmentationSource Free Object Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Image Classification CIFAR-10, 250 Labels MeanTeacher Percentage error 47.32 #25 of 27 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels Mean Teacher Percentage error 6.28 #31 of 49 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data Mean Teacher (ResNeXt-152) Top 5 Accuracy 90.89% #51 of 75 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels Mean Teacher Accuracy 96.05 #13 of 17 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 250 Labels MeanTeacher Accuracy 93.55 #11 of 15 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Voxel) mIoU (1% Labels) 41.0 #2 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Voxel) mIoU (10% Labels) 50.1 #2 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Voxel) mIoU (20% Labels) 52.8 #2 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Voxel) mIoU (50% Labels) 53.9 #2 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Range View) mIoU (1% Labels) 34.2 #7 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Range View) mIoU (10% Labels) 49.8 #7 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Range View) mIoU (20% Labels) 51.6 #7 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation ScribbleKITTI MeanTeacher (Range View) mIoU (50% Labels) 53.3 #7 of 9 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Voxel) mIoU (1% Labels) 45.4 #7 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Voxel) mIoU (10% Labels) 57.1 #7 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Voxel) mIoU (20% Labels) 59.2 #7 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Voxel) mIoU (50% Labels) 60.0 #7 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Range View) mIoU (1% Labels) 37.5 #10 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Range View) mIoU (10% Labels) 53.1 #10 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Range View) mIoU (20% Labels) 56.1 #10 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation SemanticKITTI MeanTeacher (Range View) mIoU (50% Labels) 57.4 #10 of 12 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Voxel) mIoU (1% Labels) 51.6 #4 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Voxel) mIoU (10% Labels) 66.0 #4 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Voxel) mIoU (20% Labels) 67.1 #4 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Voxel) mIoU (50% Labels) 71.7 #4 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Range View) mIoU (1% Labels) 42.1 #8 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Range View) mIoU (10% Labels) 60.4 #8 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Range View) mIoU (20% Labels) 65.4 #8 of 11 Archive leaderboard report
Semi-Supervised Semantic Segmentation nuScenes MeanTeacher (Range View) mIoU (50% Labels) 69.4 #8 of 11 Archive leaderboard report
Source Free Object Detection Cityscapes to Foggy Cityscapes MT AP50 34.3 #11 of 13 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 NormalizationConvolutionGlobal Average PoolingGrouped ConvolutionKaiming InitializationReLUResNeXtResNeXt 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