Papers › Improved Techniques for Training GANs

Improved Techniques for Training GANs

10 Jun 2016NeurIPS 2016 12arXiv:1606.03498archive 2025-07-28

Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen

We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. We focus on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic. Unlike most work on generative models, our primary goal is not to train a model that assigns high likelihood to test data, nor do we require the model to be able to learn well without using any labels. Using our new techniques, we achieve state-of-the-art results in semi-supervised classification on MNIST, CIFAR-10 and SVHN. The generated images are of high quality as confirmed by a visual Turing test: our model generates MNIST samples that humans cannot distinguish from real data, and CIFAR-10 samples that yield a human error rate of 21.3%. We also present ImageNet samples with unprecedented resolution and show that our methods enable the model to learn recognizable features of ImageNet classes.

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 repositories (openai/improved-gan, openai/improved_gan) were not harvested; the 2 samples below come from 2 community repositories.

Syntology 2 code samples harvested from 2 repositories linked to this paper: 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) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 2 samples from 2 repositories, 1 ran (0 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 9 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.

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

openai/improved-gan officialmentioned in papertfSyntology: not harvested report
openai/improved_gan officialmentioned in papertfSyntology: not harvested report
BeyondCloud/Comp04_ReverseImageCaption mentioned on GitHubtfSyntology: not harvested report
Kyan-Ge/Semi-supervised-Gan mentioned on GitHubpytorchSyntology: not harvested report
LsAntonio/60daysofudacity mentioned on GitHubpytorchSyntology: not harvested report
TahmasbiM/Example mentioned on GitHubtfSyntology: not harvested report
TomokiKomiya/SRGAN-keras mentioned on GitHubtfSyntology: not harvested report
Vishal-V/StackGAN mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks (arXiv:1612.03242; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
WGLab/SGAN mentioned on GitHubpytorchSyntology: not harvested report
ZhimingZhou/AM-GAN mentioned on GitHubtfSyntology: not harvested report
aelnouby/Text-to-Image-Synthesis mentioned on GitHubpytorchSyntology: not harvested report
agupta231/CARROL mentioned on GitHubtfSyntology: not harvested report
andrearama/Deep-Auxiliary-Classifier-GAN mentioned on GitHubpytorchSyntology: not harvested report
arnonbruno/ganify mentioned on GitHubtfMITSyntology: not harvested report
chameleonTK/continual-learning-for-HAR mentioned on GitHubpytorchSyntology: not harvested report
daixiangzi/ImprovedGan-pytorch mentioned on GitHubpytorchSyntology: not harvested report
deepak112/Keras-SRGAN mentioned on GitHubtfSyntology: not harvested report
djsinghnegi/SRINImageEnhancemrntGAN mentioned on GitHubtfSyntology: not harvested report
fastforwardlabs/deepad mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Learning for Anomaly Detection: A Survey (arXiv:1901.03407; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
fmorenovr/Semi-Supervised-Learning_with_GAN_Keras mentioned on GitHubtfSyntology: not harvested report
francis-kang/handson-unsupervised-learning mentioned on GitHubtfSyntology: not harvested report
franroldans/tfm-franroldan-wav2pix mentioned on GitHubpytorchSyntology: not harvested report
geekysethi/triplet-GAN mentioned on GitHubpytorchSyntology: not harvested report
hanzhanggit/StackGAN-inception-model mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generative Adversarial Text to Image Synthesis (arXiv:1605.05396; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
healthcare-robotics/mr-gan mentioned on GitHubSyntology: not harvested report
helmy-elrais/Semi_Supervised_Learning mentioned on GitHubpytorchSyntology: not harvested report
mlz8/GAN-Reading-List mentioned on GitHubSyntology: not harvested report
nanwei1/MNIST_GAN mentioned on GitHubpytorchSyntology: not harvested report
nupurkmr9/vision-aided-gan mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Ensembling Off-the-shelf Models for GAN Training (arXiv:2112.09130; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
raahii/evan mentioned on GitHubpytorchSyntology: not harvested report
raahii/video-gans-evaluation mentioned on GitHubpytorchSyntology: not harvested report
sanghviyashiitb/GANS-VanillaAndMinibatchDiscrimination mentioned on GitHubpytorchSyntology: not harvested report
sbarratt/inception-score-pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Exposing flaws of generative model evaluation metrics and their unfair treatment of... (arXiv:2306.04675; that paper's own run record: 53 ran (of which 0 constructed an object rather than computing a result; 30 with no instrument failure: 6 honoured, 1 violated, 23 with no contract checked; 23 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
snow-mn/GAN-INT-CLS mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Training of Wasserstein GANs (arXiv:1704.00028; that paper's own run record: 27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
t0nberryking/DCGAN256 mentioned on GitHubSyntology: not harvested report
tdrussell/IllustrationGAN mentioned on GitHubtfSyntology: not harvested report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), 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), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
theidentity/Improved-GAN-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
tsc2017/Inception-Score mentioned on GitHubtfApache-2.0Syntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
victordibia/deepad mentioned on GitHubtfApache-2.0Syntology: not harvested report
vuanhtu1993/Keras-SRGANs mentioned on GitHubtfSyntology: not harvested report
watsonyanghx/GAN_Lib_Tensorflow mentioned on GitHubtfSyntology: not harvested report
wilson1yan/VideoGPT mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generating Long Sequences with Sparse Transformers (arXiv:1904.10509; that paper's own run record: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
zhenxuan00/triple-gan mentioned on GitHubpytorchSyntology: not harvested report
MaximeVandegar/Papers-in-100-Lines-of-Code pytorchSyntology: 1 sample, 0 ran · 1 unverified 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

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

2 samples harvested: 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) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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
1unverified

Licence: 0 of the 2 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 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.

tsc2017/Inception-Score community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
preds2score in 5 papers inception_score.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a32f853e4b62793c · report fixture: signature preds:ndarray/2/float, splits:int/0/int · returned tuple · level recorded 2026-09-22
MaximeVandegar/Papers-in-100-Lines-of-Code community (archive-listed) 1 sample, 0 ran · 1 unverified
train in 522 papers Improved_Techniques_for_Training_GANs/semi_supervised_learning.py unverified MIT (permissive) · b855806c84babb76 · report

Tasks

Conditional Image GenerationImage GenerationSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Image Generation CIFAR-10 Improved GAN Inception score 8.09 #21 of 25 Archive leaderboard report
Image Classification SVHN Improved GAN Percentage error 8.11 #44 of 62 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels GAN Percentage error 15.59 #48 of 49 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels GAN Accuracy 91.89 #17 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: GAN Feature Matching, Minibatch Discrimination, Virtual Batch Normalization

Batch NormalizationConvolutionGAN Feature MatchingLabel SmoothingMinibatch DiscriminationVirtual Batch NormalizationWeight Normalization

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