Papers › Meta Pseudo Labels

Meta Pseudo Labels

23 Mar 2020CVPR 2021 1arXiv:2003.10580archive 2025-07-28

Hieu Pham, Zihang Dai, Qizhe Xie, Minh-Thang Luong, Quoc V. Le

We present Meta Pseudo Labels, a semi-supervised learning method that achieves a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the existing state-of-the-art. Like Pseudo Labels, Meta Pseudo Labels has a teacher network to generate pseudo labels on unlabeled data to teach a student network. However, unlike Pseudo Labels where the teacher is fixed, the teacher in Meta Pseudo Labels is constantly adapted by the feedback of the student's performance on the labeled dataset. As a result, the teacher generates better pseudo labels to teach the student. Our code will be available at https://github.com/google-research/google-research/tree/master/meta_pseudo_labels.

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

No sample from the archive's official repository (google-research/google-research) is linked to this paper; the 14 samples below come from 2 community repositories. Syntology harvested code from google-research/google-research for 24 other papers.

google-research/google-research: Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 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), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

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; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 5 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 (7 with no instrument failure; 5 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/google-research officialtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Neural Architecture Search via Parameter Sharing (arXiv:1802.03268; that paper's own run record: 18 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 20 unverified), Milking CowMask for Semi-Supervised Image Classification (arXiv:2003.12022; that paper's own run record: 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), Neural Additive Models: Interpretable Machine Learning with Neural Nets (arXiv:2004.13912; that paper's own run record: 26 ran (of which 14 constructed an object rather than computing a result; 26 with no instrument failure: 5 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified) and 21 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
7ZFG1/Semi-Supervised-Learning-Meta-Pseudo-Learning- mentioned on GitHubSyntology: not harvested report
YanYan0716/MPL mentioned on GitHubtfSyntology: not harvested report
kekmodel/MPL-pytorch mentioned on GitHubpytorchSyntology: not harvested report
retoschiegg/meta-pseudo-labels mentioned on GitHubtfSyntology: not harvested report
sayakpaul/PAWS-TF mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View... (arXiv:2104.13963; that paper's own run record: 19 ran (of which 4 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
usccolumbia/tsdnn mentioned on GitHubpytorchMITSyntology: 7 samples, 5 ran (2 instrument-failed) · 2 unverified report
ve450su2021-group26/Algorithm mentioned on GitHubpytorchSyntology: not harvested report
ifsheldon/MPL_Lightning pytorchMITSyntology: 7 samples, 7 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

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 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.

5ran · our draft was wrong
7ran
2unverified

Licence: 3 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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. “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.

usccolumbia/tsdnn community (archive-listed) 7 samples, 5 ran (2 instrument-failed) · 2 unverified
class_eval in 5 papers predict.py ran · our draft was wrong fingerprinted MIT (permissive) · 3f0fe82035c4dbf7 · report fixture: signature prediction:Tensor/2/float, target:Tensor/2/int · returned tuple · level recorded 2026-09-22
collate_pool tsdnn/data.py ran MIT (permissive) · 3f6dd8d427414044 · report fixture: signature dataset_list:list/1/tuple · returned tuple · level recorded 2026-09-24
get_pos_unl_val_test_loader tsdnn/data.py ran MIT (permissive) · ae57990ad886dc45 · report fixture: signature full_dataset:SimpleDatasetWithPosLen/0/?, labeled_dataset:SimpleDataset/0/?, unlabeled_dataset:SimpleDataset/0/?, collate_fn:callable/0/?, batch_size:int/0/int, train_ratio:float/0/float, val_ratio:float/0/float, test_ratio:float/0/float, return_test:bool/0/bool, num_workers:int/0/int, pin_memory:bool/0/bool, uds:bool/0/bool, train_size:NoneType/0/?, test_size:NoneType/0/?, val_size:NoneType/0/? · returned tuple · level recorded 2026-09-24
get_train_val_test_loader pu_cgcnn/cgcnn/data.py ran MIT (permissive) · 3b412198c15a2ba3 · report fixture: signature dataset:SimpleDataset/0/?, collate_fn:callable/0/?, batch_size:int/0/int, train_ratio:float/0/float, val_ratio:float/0/float, test_ratio:float/0/float, return_test:bool/0/bool, num_workers:int/0/int, pin_memory:bool/0/bool, train_size:NoneType/0/?, test_size:NoneType/0/?, val_size:NoneType/0/? · returned tuple · level recorded 2026-09-24
mae in 41 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
predict.py ran · our draft was wrong fingerprinted MIT (permissive) · 8d28ce13cc82e55f · report fixture: signature prediction:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-22
validate in 313 papers predict.py unverified MIT (permissive) · 431b44daf2725a69 · report
validate in 313 papers pu_cgcnn/cgcnn/predict.py unverified MIT (permissive) · 8d0f8832124fc89d · report
ifsheldon/MPL_Lightning community (archive-listed) 7 samples, 7 ran (3 instrument-failed) · 0 unverified
AutoContrast in 30 papers mpl_lightning/augmentation.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c6e7c3451c85404f · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-24
Brightness in 31 papers mpl_lightning/augmentation.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 0d1a8d6ce2015fc7 · report fixture: signature img:Image/0/?, v:int/0/int, max_v:float/0/float, bias:float/0/float · returned Image · level recorded 2026-09-24
Color in 29 papers mpl_lightning/augmentation.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 32cb3f5760fa593e · report fixture: signature img:Image/0/?, v:int/0/int, max_v:int/0/int, bias:int/0/int · returned Image · level recorded 2026-09-24
add_data_specific_args mpl_lightning/datamodules.py ran MIT (permissive) · cc7636585a82c554 · report fixture: signature parent_parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-24
build_wideresnet in 11 papers mpl_lightning/aux_modules.py ran MIT (permissive) · 4aed6586a15047dd · report fixture: signature args:Args/0/? · returned WideResNet · level recorded 2026-09-24
get_cosine_schedule_with_warmup in 42 papers mpl_lightning/pl_modules.py ran MIT (permissive) · ddf3bcf79dbb01ce · report fixture: signature optimizer:SGD/0/?, num_warmup_steps:int/0/int, num_training_steps:int/0/int, num_wait_steps:int/0/int, num_cycles:float/0/float, last_epoch:int/0/int · returned LambdaLR · level recorded 2026-09-24
x_u_split in 5 papers mpl_lightning/datamodules.py ran MIT (permissive) · 78c331f531a14ce5 · report fixture: signature labels:list/1/int, num_labeled:int/0/int, num_classes:int/0/int, expand_labels:bool/0/bool, batch_size:int/0/int, eval_step:int/0/int · returned tuple · level recorded 2026-09-24

Tasks

Image ClassificationMeta-LearningSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet Meta Pseudo Labels (EfficientNet-L2) Hardware Burden 95040G #6 of 1060 Archive leaderboard report
Image Classification ImageNet Meta Pseudo Labels (EfficientNet-L2) Number of params 480M #6 of 1060 Archive leaderboard report
Image Classification ImageNet Meta Pseudo Labels (EfficientNet-L2) Top 1 Accuracy 90.2% #6 of 1060 Archive leaderboard report
Image Classification ImageNet Meta Pseudo Labels (EfficientNet-L2) Top 5 Accuracy 98.8 #6 of 1060 Archive leaderboard report
Image Classification ImageNet Meta Pseudo Labels (EfficientNet-B6-Wide) Number of params 390M #10 of 1060 Archive leaderboard report
Image Classification ImageNet Meta Pseudo Labels (EfficientNet-B6-Wide) Top 1 Accuracy 90% #10 of 1060 Archive leaderboard report
Image Classification ImageNet Meta Pseudo Labels (ResNet-50) Top 1 Accuracy 83.2% #448 of 1060 Archive leaderboard report
Image Classification ImageNet ReaL Meta Pseudo Labels (EfficientNet-B6-Wide) Accuracy 91.12% #4 of 57 Archive leaderboard report
Image Classification ImageNet ReaL Meta Pseudo Labels (EfficientNet-L2) Accuracy 91.02% #8 of 57 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels Meta Pseudo Labels (WRN-28-2) Percentage error 3.89± 0.07 #5 of 49 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data Meta Pseudo Labels (ResNet-50) Top 1 Accuracy 73.89% #34 of 75 Archive leaderboard report
Semi-Supervised Image Classification ImageNet - 10% labeled data Meta Pseudo Labels (ResNet-50) Top 5 Accuracy 91.38% #34 of 75 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels Meta Pseudo Labels (WRN-28-2) Accuracy 98.01 ± 0.07 #1 of 17 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: Meta Pseudo Labels

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetGlobal Average PoolingInverted Residual BlockKaiming InitializationMax PoolingMeta Pseudo LabelsPointwise ConvolutionRMSPropReLUResidual BlockResidual ConnectionSigmoid ActivationSqueeze-and-Excitation Block

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