Papers › Learning from Simulated and Unsupervised Images through Adversarial Training

Learning from Simulated and Unsupervised Images through Adversarial Training

22 Dec 2016CVPR 2017 7arXiv:1612.07828archive 2025-07-28

Ashish Shrivastava, Tomas Pfister, Oncel Tuzel, Josh Susskind, Wenda Wang, Russ Webb

With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due to a gap between synthetic and real image distributions. To reduce this gap, we propose Simulated+Unsupervised (S+U) learning, where the task is to learn a model to improve the realism of a simulator's output using unlabeled real data, while preserving the annotation information from the simulator. We develop a method for S+U learning that uses an adversarial network similar to Generative Adversarial Networks (GANs), but with synthetic images as inputs instead of random vectors. We make several key modifications to the standard GAN algorithm to preserve annotations, avoid artifacts, and stabilize training: (i) a 'self-regularization' term, (ii) a local adversarial loss, and (iii) updating the discriminator using a history of refined images. We show that this enables generation of highly realistic images, which we demonstrate both qualitatively and with a user study. We quantitatively evaluate the generated images by training models for gaze estimation and hand pose estimation. We show a significant improvement over using synthetic images, and achieve state-of-the-art results on the MPIIGaze dataset without any labeled real data.

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

Syntology 8 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 2 repositories, 6 ran (5 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.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

AlexHex7/SimGAN_pytorch mentioned on GitHubpytorchSyntology: not harvested report
adnanalam53/cycleGAN mentioned on GitHubtfSyntology: not harvested report
ajdillhoff/simgan-pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
ashkanpakzad/atn mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
carpedm20/simulated-unsupervised-tensorflow mentioned on GitHubtfApache-2.0Syntology: 6 samples, 6 ran (1 instrument-failed) · 0 unverified report
mjdietzx/SimGAN mentioned on GitHubtfMITSyntology: 2 samples, 0 ran · 2 unverified report
rickyhan/SimGAN-Captcha mentioned on GitHubtfSyntology: not harvested report
rvorias/uvHolographics mentioned on GitHubGPL-2.0Syntology: not harvested report
shinseung428/simGAN_NYU_Hand mentioned on GitHubtfSyntology: not harvested 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

8 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 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 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 · violated contract
1ran · our draft was wrong
4ran
2unverified

Licence: 1 of the 8 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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.

carpedm20/simulated-unsupervised-tensorflow community (archive-listed) 6 samples, 6 ran (1 instrument-failed) · 0 unverified
add_argument_group in 31 papers config.py ran · our draft was wrong Apache-2.0 (permissive) · 6d80592fd6d47b2d · report fixture: signature name:str/0/str · returned _ArgumentGroup · level recorded 2026-09-22
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
layers.py ran fingerprinted Apache-2.0 (permissive) · 78fe835ab7648084 · report fixture: signature layer:Tensor/2/float · returned Tensor · level recorded 2026-09-26
img_tile utils.py ran Apache-2.0 (permissive) · 596604194d95dd97 · report fixture: signature imgs:ndarray/3/int, aspect_ratio:float/0/float, tile_shape:NoneType/0/?, border:int/0/int, border_color:int/0/int · returned ndarray · level recorded 2026-09-26
int_shape in 6 papers layers.py ran Apache-2.0 (permissive) · d8048bd9bbcd6ea7 · report fixture: signature x:EagerTensor/2/float · returned list · level recorded 2026-09-26
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
layers.py ran fingerprinted Apache-2.0 (permissive) · 4e4f748b288adeb8 · report fixture: signature layer:Tensor/2/float · returned Tensor · level recorded 2026-09-26
str2bool in 533 papers config.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · 248284f69adfeaad · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
mjdietzx/SimGAN community (archive-listed) 2 samples, 0 ran · 2 unverified
discriminator_network sim-gan.py unverified MIT (permissive) · 8333c52a9c7d2179 · report
refiner_network sim-gan.py unverified MIT (permissive) · 72f47073731f2382 · report

Tasks

Domain AdaptationGaze EstimationHand Pose EstimationImage-to-Image TranslationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-to-Image Translation Cityscapes Labels-to-Photo SimGAN Class IOU 0.04 #19 of 21 Archive leaderboard report
Image-to-Image Translation Cityscapes Labels-to-Photo SimGAN Per-class Accuracy 10% #19 of 21 Archive leaderboard report
Image-to-Image Translation Cityscapes Labels-to-Photo SimGAN Per-pixel Accuracy 20% #19 of 21 Archive leaderboard report
Image-to-Image Translation Cityscapes Photo-to-Labels SimGAN Class IOU 0.07 #5 of 5 Archive leaderboard report
Image-to-Image Translation Cityscapes Photo-to-Labels SimGAN Per-class Accuracy 11% #5 of 5 Archive leaderboard report
Image-to-Image Translation Cityscapes Photo-to-Labels SimGAN Per-pixel Accuracy 47% #5 of 5 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

Convolution

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