Papers › Differentiable Augmentation for Data-Efficient GAN Training

Differentiable Augmentation for Data-Efficient GAN Training

18 Jun 2020NeurIPS 2020 12arXiv:2006.10738archive 2025-07-28

Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu, Song Han

The performance of generative adversarial networks (GANs) heavily deteriorates given a limited amount of training data. This is mainly because the discriminator is memorizing the exact training set. To combat it, we propose Differentiable Augmentation (DiffAugment), a simple method that improves the data efficiency of GANs by imposing various types of differentiable augmentations on both real and fake samples. Previous attempts to directly augment the training data manipulate the distribution of real images, yielding little benefit; DiffAugment enables us to adopt the differentiable augmentation for the generated samples, effectively stabilizes training, and leads to better convergence. Experiments demonstrate consistent gains of our method over a variety of GAN architectures and loss functions for both unconditional and class-conditional generation. With DiffAugment, we achieve a state-of-the-art FID of 6.80 with an IS of 100.8 on ImageNet 128x128 and 2-4x reductions of FID given 1,000 images on FFHQ and LSUN. Furthermore, with only 20% training data, we can match the top performance on CIFAR-10 and CIFAR-100. Finally, our method can generate high-fidelity images using only 100 images without pre-training, while being on par with existing transfer learning algorithms. Code is available at https://github.com/mit-han-lab/data-efficient-gans.

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 58 code samples harvested from 11 repositories linked to this paper: 49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 11 where our contract draft was wrong; 21 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 7 ran (0 with no instrument failure; 7 where Syntology's instrument failed); community (archive-listed): 51 samples from 10 repositories, 42 ran (17 with no instrument failure; 25 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 1 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. 5 of the 49 samples that ran have no recorded date.

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

mit-han-lab/data-efficient-gans officialmentioned in papermentioned on GitHubtfSyntology: 7 samples, 7 ran (7 instrument-failed) · 0 unverified report
POSTECH-CVLab/PyTorch-StudioGAN mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
VITA-Group/Ultra-Data-Efficient-GAN-Training mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
claim-berlin/3d_stylegan_circle_of_willis mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (4 instrument-failed) · 1 unverified report
eps696/stylegan2 mentioned on GitHubtfSyntology: 6 samples, 6 ran (5 instrument-failed) · 0 unverified report
gaborvecsei/SLE-GAN mentioned on GitHubtfSyntology: 6 samples, 6 ran (5 instrument-failed) · 0 unverified report
milmor/LadaGAN-pytorch mentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (2 instrument-failed) · 2 unverified report
milmor/TransGAN mentioned on GitHubtfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
milmor/ladagan mentioned on GitHubtfMITSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
milmor/self-supervised-gan mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
shreshtashetty/CycleGANPhototoMonet mentioned on GitHubSyntology: not harvested report
uzielroy/StyleGan_FewShot mentioned on GitHubpytorchMITSyntology: 14 samples, 10 ran (4 instrument-failed) · 4 unverified report
jankrepl/mildlyoverfitted jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Axiomatic Attribution for Deep Networks (arXiv:1703.01365; that paper's own run record: 36 ran (of which 13 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 15 where Syntology's instrument failed) · 20 unverified), mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 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; 22 where Syntology's instrument failed) · 11 unverified), The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (arXiv:1803.03635; that paper's own run record: 12 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified) and 6 more (every one in this page's JSON twin); 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

58 samples harvested: 49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 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.

3ran · honoured contract
1ran · violated contract
11ran · our draft was wrong
21ran; the contract check could not run
13ran
9unverified

Licence: 15 of the 58 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 11 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.

mit-han-lab/data-efficient-gans official repository 7 samples, 7 ran (7 instrument-failed) · 0 unverified
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
DiffAugment_pytorch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted BSD-2-Clause (permissive) · b0bbabd6de30f612 · report fixture: signature x:Tensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned Tensor · level recorded, date not recorded
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
DiffAugment_pytorch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted BSD-2-Clause (permissive) · 5a98bf7c8a33d10d · report fixture: signature x:Tensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned Tensor · level recorded 2026-09-22
rand_brightness in 25 papers
census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
DiffAugment_pytorch.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) · fd66a45971195f9a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
rand_contrast in 7 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
DiffAugment_pytorch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted BSD-2-Clause (permissive) · cf3f99cfbe8f451a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
rand_cutout in 7 papers
census: 6 implementations from 6 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
DiffAugment_pytorch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted BSD-2-Clause (permissive) · 8a8f1bb31f56eb41 · report fixture: signature x:Tensor/4/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-22
rand_saturation in 24 papers
census: 6 implementations from 9 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
DiffAugment_pytorch.py ran · our draft was wrong fingerprinted BSD-2-Clause (permissive) · abafb0afcfb5d028 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
rand_translation DiffAugment_pytorch.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted BSD-2-Clause (permissive) · 64f17a01e2d642b0 · report fixture: signature x:Tensor/4/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-22
POSTECH-CVLab/PyTorch-StudioGAN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
apply_diffaug src/utils/diffaug.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 11fe0ba0c9c1c2ba · report fixture: signature x:Tensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned Tensor · level recorded 2026-09-22
VITA-Group/Ultra-Data-Efficient-GAN-Training community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
BigGAN and DiffAugGAN/utils/diff_aug.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · b13ee69651d4b880 · report fixture: signature x:Tensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned Tensor · level recorded 2026-09-22
rand_translation BigGAN and DiffAugGAN/utils/diff_aug.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 4cfe42eb20e188c9 · report fixture: signature x:Tensor/4/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-22
claim-berlin/3d_stylegan_circle_of_willis community (archive-listed) 5 samples, 4 ran (4 instrument-failed) · 1 unverified
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 5, kind float, dtype float32
diff_augment.py ran · our draft was wrong licence not identified · pointer only · aff3959c75a4b707 · report fixture: signature x:Tensor/5/float, types:list/1/str · returned Tensor · level recorded 2026-09-22
rand_brightness in 25 papers
census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 5, kind float, dtype float32
diff_augment.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 0054342024c45e46 · report fixture: signature x:Tensor/5/float, scale:float/0/float · returned Tensor · level recorded 2026-09-22
rand_contrast in 7 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 5, kind float, dtype float32
diff_augment.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 93a3d74d32b20296 · report fixture: signature x:Tensor/5/float, scale:float/0/float · returned Tensor · level recorded 2026-09-22
rand_translation diff_augment.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 164a3d8cb51836fd · report fixture: signature x:Tensor/5/float, ratio:float/0/float · returned Tensor · level recorded 2026-09-22
rand_cutout in 7 papers
census: 6 implementations from 6 papers, 4 distinct outputs on one shared input
diff_augment.py unverified licence not identified · pointer only · 390fc5d117993c38 · report
eps696/stylegan2 community (archive-listed) 6 samples, 6 ran (5 instrument-failed) · 0 unverified
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
src/training/DiffAugment_tf.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 719b769b10895fa0 · report fixture: signature x:EagerTensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
rand_brightness in 25 papers
census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
src/training/DiffAugment_tf.py ran · honoured contract fingerprinted licence not identified · pointer only · 23b9e86dc02652cc · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
rand_contrast in 7 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/training/DiffAugment_tf.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 7668b11c66661278 · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
rand_cutout in 7 papers
census: 6 implementations from 6 papers, 4 distinct outputs on one shared input
src/training/DiffAugment_tf.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · d3f6dbbf7ed4b605 · report fixture: signature x:EagerTensor/4/float, ratio:float/0/float · returned EagerTensor · level recorded 2026-09-22
rand_saturation in 24 papers
census: 6 implementations from 9 papers, 3 distinct outputs on one shared input
src/training/DiffAugment_tf.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · c8f9bf34313b879d · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
rand_translation src/training/DiffAugment_tf.py ran; the contract check could not run (RAISES) fingerprinted licence not identified · pointer only · 5895184332d50243 · report fixture: signature x:EagerTensor/4/float, ratio:float/0/float · returned EagerTensor · level recorded 2026-09-22
gaborvecsei/SLE-GAN community (archive-listed) 6 samples, 6 ran (5 instrument-failed) · 0 unverified
diff_augment sle_gan/diff_augment.py ran; the contract check could not run (RAISES) MIT (permissive) · 4e9a3e9a819d11b0 · report fixture: returned EagerTensor · level recorded 2026-09-22
rand_brightness in 25 papers
census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
sle_gan/diff_augment.py ran · honoured contract MIT (permissive) · c0fd34aac0b4d83d · report fixture: returned EagerTensor · level recorded 2026-09-22
rand_contrast in 7 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
sle_gan/diff_augment.py ran; the contract check could not run (RAISES) MIT (permissive) · 1ea606a1b578d9fd · report fixture: returned EagerTensor · level recorded 2026-09-22
rand_cutout in 7 papers
census: 6 implementations from 6 papers, 4 distinct outputs on one shared input
sle_gan/diff_augment.py ran; the contract check could not run (RAISES) MIT (permissive) · 7eedee91371852fd · report fixture: returned EagerTensor · level recorded 2026-09-22
rand_saturation in 24 papers
census: 6 implementations from 9 papers, 3 distinct outputs on one shared input
sle_gan/diff_augment.py ran; the contract check could not run (RAISES) MIT (permissive) · fe6b745a5727de14 · report fixture: returned EagerTensor · level recorded 2026-09-22
rand_translation sle_gan/diff_augment.py ran; the contract check could not run (RAISES) MIT (permissive) · 3960a5e348576c26 · report fixture: returned EagerTensor · level recorded 2026-09-22
milmor/LadaGAN-pytorch community (archive-listed) 10 samples, 8 ran (2 instrument-failed) · 2 unverified
create_loader in 6 papers image_datasets.py ran MIT (permissive) · 0c5eecc2f5f4579c · report fixture: signature data_dir:str/0/str, img_size:int/0/int, batch_size:int/0/int, workers:int/0/int, pin_memory:bool/0/bool · returned _MultiProcessingDataLoaderIter · level recorded 2026-09-24
d_logistic_loss in 15 papers
census: 2 implementations from 7 papers, 1 distinct output on one shared input
utils.py ran fingerprinted MIT (permissive) · dfe4839c7c03b7fa · report fixture: signature real_pred:Tensor/2/float, fake_pred:Tensor/2/float · returned Tensor · level recorded 2026-09-24
d_r1_loss in 10 papers utils.py ran MIT (permissive) · 0143fef228211c97 · report fixture: signature real_pred:Tensor/2/float, real_img:Tensor/4/float · returned Tensor · level recorded 2026-09-24
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
utils.py ran fingerprinted MIT (permissive) · 05e9b8206464518b · report fixture: signature image:Tensor/2/float · returned Tensor · level recorded 2026-09-24
list_image_files image_datasets.py ran MIT (permissive) · 9b9d7e8b8644417b · report fixture: signature data_dir:str/0/str · returned list · level recorded 2026-09-24
pixel_upsample model.py ran MIT (permissive) · 79d4e2efdb8db1f5 · report fixture: signature x:Tensor/3/float, H:int/0/int, W:int/0/int · returned tuple · level recorded 2026-09-24
rand_brightness in 25 papers
census: 7 implementations from 9 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32
diffaug.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 011230b2b9b8fb6f · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
rand_saturation in 24 papers
census: 6 implementations from 9 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
diffaug.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 5b0d8787e670fc63 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded, date not recorded
calculate_activation_statistics in 75 papers fid.py unverified MIT (permissive) · c5a04d1cab5f16a8 · report
get_activations in 100 papers fid.py unverified MIT (permissive) · 63749a9f8d05d87c · report
milmor/TransGAN community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
diffaug.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 9f13704fe37f3a7f · report fixture: signature x:EagerTensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
rand_cutout in 7 papers
census: 6 implementations from 6 papers, 4 distinct outputs on one shared input
diffaug.py ran · violated contract fingerprinted MIT (permissive) · d2d7ad30f29efa00 · report fixture: signature x:EagerTensor/4/float, ratio:float/0/float · returned EagerTensor · level recorded 2026-09-22
milmor/ladagan community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
calculate_frechet_distance in 119 papers tensorflow/fid.py ran MIT (permissive) · 7bd28928af1bae66 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-24
get_map in 5 papers tensorflow/plot_utils.py ran MIT (permissive) · 60afeee00005b62b · report fixture: signature maps:dict/0/?, resolution:str/0/str, head:int/0/int · returned EagerTensor · level recorded 2026-09-24
l2_loss in 136 papers tensorflow/trainer.py unverified MIT (permissive) · 76bc532052b7504c · report
pixel_upsample tensorflow/model.py unverified MIT (permissive) · d4eb4c7282c41f98 · report
milmor/self-supervised-gan community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
DiffAugment in 28 papers
census: 7 implementations from 5 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
diffaug.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 106e066ecaa411cb · report fixture: signature x:EagerTensor/4/float, policy:str/0/str, channels_first:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
uzielroy/StyleGan_FewShot community (archive-listed) 14 samples, 10 ran (4 instrument-failed) · 4 unverified
calc_distances save_images_monet.py ran fingerprinted MIT (permissive) · 591df4f8315785cd · report fixture: signature p0:ndarray/1/float, points:ndarray/2/float · returned ndarray · level recorded 2026-09-24
calculate_frechet_distance in 119 papers metric/fid_score.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · 4cee7c1861294d59 · report fixture: signature mu1:ndarray/1/float, sigma1:ndarray/2/float, mu2:ndarray/1/float, sigma2:ndarray/2/float, eps:float/0/float · returned float64 · level recorded 2026-09-22
equal_lr in 11 papers model.py ran · our draft was wrong MIT (permissive) · 5ef2eff36d9c9c0e · report fixture: signature module:callable/0/?, name:str/0/str · returned SimpleModule · level recorded 2026-09-22
get_gaussian_kernel in 17 papers metric/swd_score.py ran · honoured contract MIT (permissive) · c8ceba12b6020549 · report fixture: signature device:str/0/str · returned Tensor · level recorded 2026-09-24
graipher save_images_monet.py ran MIT (permissive) · e176b3170e9eb7f9 · report fixture: signature pts:ndarray/2/float, K:int/0/int · returned tuple · level recorded 2026-09-24
l2_reg finetune.py ran MIT (permissive) · 3d111932e00fa877 · report fixture: signature net_src:callable/0/?, net_tgt:callable/0/? · returned Tensor · level recorded 2026-09-24
polynomial_mmd in 7 papers metric/kid_score.py ran MIT (permissive) · 8fdb950a259799fe · report fixture: signature codes_r:ndarray/2/float, codes_g:ndarray/2/float, degree:int/0/int, gamma:NoneType/0/?, coef0:int/0/int, var_at_m:NoneType/0/?, ret_var:bool/0/bool · returned tuple · level recorded 2026-09-24
polynomial_mmd_averages metric/kid_score.py ran MIT (permissive) · afe497bbaa6085f4 · report fixture: signature codes_r:ndarray/2/float, codes_g:ndarray/2/float, n_subsets:int/0/int, subset_size:int/0/int, ret_var:bool/0/bool, replace:bool/0/bool · returned tuple · level recorded 2026-09-24
pyramid_down metric/swd_score.py ran · our draft was wrong MIT (permissive) · 4a3a50d5b90d9dac · report fixture: signature image:Tensor/4/float, device:str/0/str · returned Tensor · level recorded 2026-09-24
pyramid_up metric/swd_score.py ran · our draft was wrong MIT (permissive) · d6f847810616ed82 · report fixture: signature image:Tensor/4/float, device:str/0/str · returned Tensor · level recorded 2026-09-24
FM_reg finetune.py unverified MIT (permissive) · a76fa2aebbbe157d · report
calculate_activation_statistics in 75 papers metric/fid_score.py unverified MIT (permissive) · 9128352cd567690a · report
get_activations in 100 papers metric/fid_score.py unverified MIT (permissive) · a3ef5898d81d8dd1 · report
images_pca save_images_monet.py unverified MIT (permissive) · e997ac6a2c12732a · 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.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for DiffAugment (graph method: DiffAugment). 6 bricks; individually on a fixture: 6 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; 6 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. DiffAugment entry · level 1 · ran; the contract check could not run (RAISES) · b13ee69651d4b880
  2. rand_brightness data_transform · level 1 · ran · our draft was wrong · 011230b2b9b8fb6f
  3. rand_contrast data_transform · level 1 · ran; the contract check could not run (RAISES) · cf3f99cfbe8f451a
  4. rand_cutout data_transform · level 1 · ran; the contract check could not run (RAISES) · 8a8f1bb31f56eb41
  5. rand_saturation data_transform · level 1 · ran · our draft was wrong · 5b0d8787e670fc63
  6. rand_translation data_transform · level 1 · ran; the contract check could not run (RAISES) · 4cfe42eb20e188c9

harvested Assembly for DiffAugment (graph method: DiffAugment). 6 bricks; individually on a fixture: 6 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; 5 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. diff_augment entry · level 1 · ran; the contract check could not run (RAISES) · 4e9a3e9a819d11b0
  2. rand_brightness data_transform · level 1 · ran · honoured contract · c0fd34aac0b4d83d
  3. rand_contrast data_transform · level 1 · ran; the contract check could not run (RAISES) · 1ea606a1b578d9fd
  4. rand_cutout data_transform · level 1 · ran; the contract check could not run (RAISES) · 7eedee91371852fd
  5. rand_saturation data_transform · level 1 · ran; the contract check could not run (RAISES) · fe6b745a5727de14
  6. rand_translation data_transform · level 1 · ran; the contract check could not run (RAISES) · 3960a5e348576c26

harvested Assembly for DiffAugment (graph method: DiffAugment). 6 bricks; individually on a fixture: 6 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; 5 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. DiffAugment entry · level 1 · ran; the contract check could not run (RAISES) · 106e066ecaa411cb
  2. rand_brightness data_transform · level 1 · ran · honoured contract · c0fd34aac0b4d83d
  3. rand_contrast data_transform · level 1 · ran; the contract check could not run (RAISES) · 1ea606a1b578d9fd
  4. rand_cutout data_transform · level 1 · ran; the contract check could not run (RAISES) · 7eedee91371852fd
  5. rand_saturation data_transform · level 1 · ran; the contract check could not run (RAISES) · fe6b745a5727de14
  6. rand_translation data_transform · level 1 · ran; the contract check could not run (RAISES) · 3960a5e348576c26

harvested Assembly for DiffAugment (graph method: DiffAugment). 6 bricks; individually on a fixture: 6 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; 5 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. DiffAugment entry · level 1 · ran; the contract check could not run (RAISES) · 719b769b10895fa0
  2. rand_brightness data_transform · level 1 · ran · honoured contract · 23b9e86dc02652cc
  3. rand_contrast data_transform · level 1 · ran; the contract check could not run (RAISES) · 7668b11c66661278
  4. rand_cutout data_transform · level 1 · ran; the contract check could not run (RAISES) · d3f6dbbf7ed4b605
  5. rand_saturation data_transform · level 1 · ran; the contract check could not run (RAISES) · c8f9bf34313b879d
  6. rand_translation data_transform · level 1 · ran; the contract check could not run (RAISES) · 5895184332d50243

harvested Assembly for DiffAugment (graph method: DiffAugment). 6 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. DiffAugment entry · level 1 · ran; the contract check could not run (RAISES) · 9f13704fe37f3a7f
  2. rand_brightness data_transform · level 1 · ran · honoured contract · c0fd34aac0b4d83d
  3. rand_contrast data_transform · level 1 · ran; the contract check could not run (RAISES) · 1ea606a1b578d9fd
  4. rand_cutout data_transform · level 1 · ran · violated contract · d2d7ad30f29efa00
  5. rand_saturation data_transform · level 1 · ran; the contract check could not run (RAISES) · fe6b745a5727de14
  6. rand_translation data_transform · level 1 · ran; the contract check could not run (RAISES) · 3960a5e348576c26

harvested Assembly for DiffAugment (graph method: DiffAugment). 5 bricks; individually on a fixture: 4 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; 4 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. DiffAugment entry · level 1 · ran · our draft was wrong · aff3959c75a4b707
  2. rand_brightness data_transform · level 1 · ran · our draft was wrong · 0054342024c45e46
  3. rand_contrast data_transform · level 1 · ran · our draft was wrong · 93a3d74d32b20296
  4. rand_cutout data_transform · level 0 · unverified · 390fc5d117993c38
  5. rand_translation data_transform · level 1 · ran · our draft was wrong · 164a3d8cb51836fd

harvested Assembly for DiffAugment (graph method: DiffAugment). 6 bricks; individually on a fixture: 6 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; 6 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. apply_diffaug entry · level 1 · ran; the contract check could not run (RAISES) · 11fe0ba0c9c1c2ba
  2. rand_brightness helper · level 1 · ran · our draft was wrong · 011230b2b9b8fb6f
  3. rand_contrast helper · level 1 · ran; the contract check could not run (RAISES) · cf3f99cfbe8f451a
  4. rand_cutout helper · level 1 · ran; the contract check could not run (RAISES) · 8a8f1bb31f56eb41
  5. rand_saturation helper · level 1 · ran · our draft was wrong · 5b0d8787e670fc63
  6. rand_translation helper · level 1 · ran; the contract check could not run (RAISES) · 4cfe42eb20e188c9

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="2006.10738") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CIFAR-10 DiffAugment-BigGAN FID 4.61 #32 of 78 Archive leaderboard report
Image Generation CIFAR-10 (10% data) DiffAugment-StyleGAN2 FID 14.5 #1 of 3 Archive leaderboard report
Image Generation CIFAR-10 (10% data) DiffAugment-CR-BigGAN FID 18.7 #2 of 3 Archive leaderboard report
Image Generation CIFAR-10 (10% data) DiffAugment-BigGAN FID 22.4 #3 of 3 Archive leaderboard report
Image Generation CIFAR-10 (20% data) DiffAugment-StyleGAN2 FID 12.15 #1 of 3 Archive leaderboard report
Image Generation CIFAR-10 (20% data) DiffAugment-CR-BigGAN FID 12.84 #2 of 3 Archive leaderboard report
Image Generation CIFAR-10 (20% data) DiffAugment-BigGAN FID 14.04 #3 of 3 Archive leaderboard report
Image Generation ImageNet 128x128 DiffAugment-BigGAN FID 6.8 #16 of 23 Archive leaderboard report
Image Generation ImageNet 128x128 DiffAugment-BigGAN IS 100.8 #16 of 23 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: DiffAugment

1x1 ConvolutionAdamBatch NormalizationBigGANColorJitterConditional Batch NormalizationConvolutionCutoutDense ConnectionsDiffAugmentEarly StoppingFeedforward NetworkGAN Hinge LossLinear LayerNon-Local BlockNon-Local OperationOff-Diagonal Orthogonal RegularizationPath Length RegularizationProjection DiscriminatorR1 RegularizationReLUResidual BlockResidual ConnectionSAGANSoftmaxSpectral NormalizationStyleGAN2TTURTruncation TrickWeight Demodulation

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