Papers › RandAugment: Practical automated data augmentation with a reduced search space

RandAugment: Practical automated data augmentation with a reduced search space

30 Sep 2019NeurIPS 2020 12arXiv:1909.13719archive 2025-07-28

Ekin D. Cubuk, Barret Zoph, Jonathon Shlens, Quoc V. Le

Recent work has shown that data augmentation has the potential to significantly improve the generalization of deep learning models. Recently, automated augmentation strategies have led to state-of-the-art results in image classification and object detection. While these strategies were optimized for improving validation accuracy, they also led to state-of-the-art results in semi-supervised learning and improved robustness to common corruptions of images. An obstacle to a large-scale adoption of these methods is a separate search phase which increases the training complexity and may substantially increase the computational cost. Additionally, due to the separate search phase, these approaches are unable to adjust the regularization strength based on model or dataset size. Automated augmentation policies are often found by training small models on small datasets and subsequently applied to train larger models. In this work, we remove both of these obstacles. RandAugment has a significantly reduced search space which allows it to be trained on the target task with no need for a separate proxy task. Furthermore, due to the parameterization, the regularization strength may be tailored to different model and dataset sizes. RandAugment can be used uniformly across different tasks and datasets and works out of the box, matching or surpassing all previous automated augmentation approaches on CIFAR-10/100, SVHN, and ImageNet. On the ImageNet dataset we achieve 85.0% accuracy, a 0.6% increase over the previous state-of-the-art and 1.0% increase over baseline augmentation. On object detection, RandAugment leads to 1.0-1.3% improvement over baseline augmentation, and is within 0.3% mAP of AutoAugment on COCO. Finally, due to its interpretable hyperparameter, RandAugment may be used to investigate the role of data augmentation with varying model and dataset size. Code is available online.

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 65 code samples: 64 from 6 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 65: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 24 where our contract draft was wrong; 27 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 64 samples from 6 repositories, 57 ran (7 with no instrument failure; 50 where Syntology's instrument failed); 1 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 9 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.

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

A-Telfer/AugKey mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Data Augmentation for Consistency Training (arXiv:1904.12848; that paper's own run record: 30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. report
adam-mehdi/MuarAugment mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On the Generalization Effects of Linear Transformations in Data Augmentation (arXiv:2005.00695; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
chenyang4/resmooth mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (2 instrument-failed) · 0 unverified report
etetteh/sota-data-augmentation-and-optimizers mentioned on GitHubpytorchSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
hitchingsh/ml-examples mentioned on GitHubtfSyntology: not harvested report
ildoonet/pytorch-randaugment mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast AutoAugment (arXiv:1905.00397; that paper's own run record: 37 ran (of which 2 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 0 violated, 19 with no contract checked; 16 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
lyxxn0414/test-data-generation mentioned on GitHubtfSyntology: 16 samples, 14 ran (14 instrument-failed) · 2 unverified report
nachiket273/pytorch_resnet_rs mentioned on GitHubpytorchSyntology: 17 samples, 15 ran (15 instrument-failed) · 2 unverified report
open-mmlab/mmpretrain mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Pixel-based MIM by Reducing Wasted Modeling Capability (arXiv:2308.00261; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
rlagywns0213/cifar100_data_augmentation mentioned on GitHubpytorchSyntology: not harvested report
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
sailist/thexp-implement mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
tensorflow/tpu mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
zhanghang1989/fast-autoaug-torch mentioned on GitHubpytorchMITSyntology: 2 samples, 0 ran · 2 unverified report
MindCode-4/code-14 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to IMMA: Immunizing text-to-image Models against Malicious Adaptation (arXiv:2311.18815; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested report
pwc-1/Paper-9 mindsporeSyntology: 20 samples, 19 ran (17 instrument-failed) · 1 unverified report
pytorch/vision pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Going Deeper with Convolutions (arXiv:1409.4842; that paper's own run record: 34 ran (of which 19 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 4 where Syntology's instrument failed) · 8 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), Deep Networks with Stochastic Depth (arXiv:1603.09382; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified) and 7 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
wangermeng2021/FastClassification tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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) and CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 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

65 samples harvested: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 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
24ran · our draft was wrong
27ran; the contract check could not run
6ran
7unverified

Licence: 17 of the 65 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 6 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. 1 sample is 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.

chenyang4/resmooth community (archive-listed) 4 samples, 4 ran (2 instrument-failed) · 0 unverified
RandAugment RandAugment/augmentations.py ran · metamorphic tier: well formed MIT (permissive) · cd8cce1f7b2b9e61 · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-22
TranslateX in 13 papers RandAugment/augmentations.py ran · our draft was wrong MIT (permissive) · f03d112eee854337 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
TranslateY RandAugment/augmentations.py ran · our draft was wrong MIT (permissive) · e02e6b30e0c6b0ab · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
augment_list RandAugment/augmentations.py ran MIT (permissive) · 0e2bfdf3982286ac · report fixture: returned list · level recorded 2026-09-22
etetteh/sota-data-augmentation-and-optimizers community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
Identity in 49 papers
census: 10 implementations from 13 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
augmentation/RandAugment.py ran · violated contract fingerprinted MIT (permissive) · 08f47bae89750cac · report fixture: signature img:Tensor/4/float, v:Tensor/2/float · returned Tensor · level recorded 2026-09-22
RandAugment augmentation/RandAugment.py ran MIT (permissive) · e097e00c2974ac62 · report fixture: returned RandAugment · level recorded 2026-09-22
TranslateX in 13 papers augmentation/RandAugment.py ran; the contract check could not run (RAISES) MIT (permissive) · b2893a9a2ac1188f · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
TranslateY augmentation/RandAugment.py ran; the contract check could not run (RAISES) MIT (permissive) · e3a2ec04026a49e8 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
augment_list augmentation/RandAugment.py ran MIT (permissive) · fa05edca4ee502d1 · report fixture: returned list · level recorded 2026-09-22
lyxxn0414/test-data-generation community (archive-listed) 16 samples, 14 ran (14 instrument-failed) · 2 unverified
auto_contrast auto_augment.py ran · our draft was wrong no licence file found · pointer only · 5ea03e170ec307dd · report fixture: signature img:ndarray/3/int, magnitude:float/0/float · returned ndarray · level recorded 2026-09-22
brightness auto_augment.py ran · our draft was wrong no licence file found · pointer only · 32a7da0ae8a21668 · report fixture: signature img:ndarray/3/int, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
color in 9 papers auto_augment.py ran · our draft was wrong no licence file found · pointer only · 747a0d64c7ffa9e5 · report fixture: signature img:ndarray/3/int, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
contrast auto_augment.py ran · our draft was wrong no licence file found · pointer only · 6d3fa2f36220efed · report fixture: signature img:ndarray/3/int, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
equalize in 10 papers auto_augment.py ran · our draft was wrong no licence file found · pointer only · 51eba7748cab33ee · report fixture: signature img:ndarray/2/int, magnitude:float/0/float · returned ndarray · level recorded 2026-09-22
invert in 12 papers auto_augment.py ran · our draft was wrong no licence file found · pointer only · a14dd4fa2af8e72e · report fixture: signature img:ndarray/3/int, magnitude:float/0/float · returned ndarray · level recorded 2026-09-22
posterize in 7 papers auto_augment.py ran · our draft was wrong no licence file found · pointer only · c2b9e317cc24e2a5 · report fixture: signature img:ndarray/3/int, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
rotate in 56 papers auto_augment.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 8d1db612602ab793 · report fixture: signature img:ndarray/3/float, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
sharpness in 9 papers auto_augment.py ran · our draft was wrong no licence file found · pointer only · 3f5e624979a30a88 · report fixture: signature img:ndarray/3/int, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
shear_x in 43 papers auto_augment.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 7fad25ebc151a21a · report fixture: signature img:ndarray/3/float, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
shear_y in 37 papers auto_augment.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · eb627b1078fe24a3 · report fixture: signature img:ndarray/3/float, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
solarize in 15 papers auto_augment.py ran · our draft was wrong no licence file found · pointer only · f5999a1ee8824e22 · report fixture: signature img:ndarray/3/int, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
translate_x in 7 papers auto_augment.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 9c2425c71cab36a2 · report fixture: signature img:ndarray/3/float, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
translate_y in 7 papers auto_augment.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · bd8449369ce2815d · report fixture: signature img:ndarray/3/float, magnitude:int/0/int · returned ndarray · level recorded 2026-09-22
apply_policy in 9 papers auto_augment.py unverified no licence file found · pointer only · 89a74c24e1285658 · report
cutout in 17 papers auto_augment.py unverified no licence file found · pointer only · 93e2ff77da69661e · report
nachiket273/pytorch_resnet_rs community (archive-listed) 17 samples, 15 ran (15 instrument-failed) · 2 unverified
autocontrast in 9 papers model/randaugment.py ran · our draft was wrong MIT (permissive) · 033f4c7eebc4b8bc · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-22
brightness model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · c853710460b412e7 · report fixture: signature img:Image/0/?, factor:float/0/float · returned Image · level recorded 2026-09-22
color in 9 papers model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 5f1efa6a7f09bf92 · report fixture: signature img:Image/0/?, factor:float/0/float · returned Image · level recorded 2026-09-22
contrast model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 74223e0d5db8f6dc · report fixture: signature img:Image/0/?, factor:float/0/float · returned Image · level recorded 2026-09-22
cutout in 17 papers model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · a07328daac80e5d4 · report fixture: signature img:Image/0/?, percentage:float/0/float · returned Image · level recorded 2026-09-22
equalize in 10 papers model/randaugment.py ran · our draft was wrong MIT (permissive) · 6f465d3353435748 · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-22
invert in 12 papers model/randaugment.py ran · our draft was wrong MIT (permissive) · b794fd0b35eea322 · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-22
posterize in 7 papers model/randaugment.py ran · our draft was wrong MIT (permissive) · ac724bc0e98f3cda · report fixture: signature img:Image/0/?, bits:int/0/int · returned Image · level recorded 2026-09-22
rotate in 56 papers model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 6d903cf9b58e8ce3 · report fixture: signature img:Image/0/?, angle:int/0/int · returned Image · level recorded 2026-09-22
sharpness in 9 papers model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · cbbf595da3dbb1fd · report fixture: signature img:Image/0/?, factor:float/0/float · returned Image · level recorded 2026-09-22
shearx model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 472154b113f3c670 · report fixture: signature img:Image/0/?, level:float/0/float · returned Image · level recorded 2026-09-22
sheary model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 9cc62c9a79622659 · report fixture: signature img:Image/0/?, level:float/0/float · returned Image · level recorded 2026-09-22
solarize in 15 papers model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · b8a2aca46dc33d3f · report fixture: signature img:Image/0/?, threshold:int/0/int · returned Image · level recorded 2026-09-22
translatex model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 845982ca54304048 · report fixture: signature img:Image/0/?, percentage:float/0/float · returned Image · level recorded 2026-09-22
translatey model/randaugment.py ran; the contract check could not run (RAISES) MIT (permissive) · 2c8f458ee8d12c14 · report fixture: signature img:Image/0/?, percentage:float/0/float · returned Image · level recorded 2026-09-22
RandAugment model/randaugment.py unverified MIT (permissive) · ad7a01616e026f1c · report
solarizeadd model/randaugment.py unverified MIT (permissive) · 3931a647e47e6c9e · report
zhanghang1989/fast-autoaug-torch community (archive-listed) 2 samples, 0 ran · 2 unverified
get_transform in 75 papers utils.py unverified MIT (permissive) · 4b57170196836cae · report
subsample_dataset in 6 papers utils.py unverified MIT (permissive) · 50c88035541deccb · report
pwc-1/Paper-9 community (archive-listed) 20 samples, 19 ran (17 instrument-failed) · 1 unverified
AutoContrast in 30 papers 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · 4a0ac9d611e018bc · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
Contrast in 5 papers 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 35f5a6d3913e6b0e · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
CutoutAbs 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 03ecbd868107e6f7 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
Equalize 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · 4befb1744e90f3a1 · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
Invert 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · f5f0bf976dfcf068 · report fixture: signature img:Image/0/?, _:NoneType/0/? · returned Image · level recorded 2026-09-22
Posterize 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · 19b3cb2d9f27fcdb · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
RandAugment 3/AVA_cifar/src/RandAugment/augmentations.py ran Apache-2.0 (permissive) · eb475b4fcf7d8891 · report fixture: signature img:Image/0/? · returned Image · level recorded 2026-09-24
Rotate in 6 papers 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · b22d322fc26595bc · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
Sharpness 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · e1ccc58bf76a30b9 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ShearX in 14 papers 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 815f704e5efd8345 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ShearY in 14 papers 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · f5e3179cafd9393a · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Solarize 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 70eab251c4b2bce2 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
ToBLUR 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · e74342905c295c87 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ToCONTOUR 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · c28a72552d33774e · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
ToEDGES 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · 6479c2b0e4d54d6a · report fixture: signature img:Image/0/?, v:NoneType/0/? · returned Image · level recorded 2026-09-22
ToEMBOSS 3/AVA_cifar/src/RandAugment/augmentations.py ran · our draft was wrong Apache-2.0 (permissive) · ce08e08f28dfcee7 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
TranslateXabs 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · d6e5e2e212d3e912 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
TranslateYabs 3/AVA_cifar/src/RandAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 52872165441774c7 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
augment_list 3/AVA_cifar/src/RandAugment/augmentations.py ran Apache-2.0 (permissive) · b6eb3433772b9aac · report fixture: returned list · level recorded 2026-09-22
SolarizeAdd 3/AVA_cifar/src/RandAugment/augmentations.py unverified Apache-2.0 (permissive) · 1c3be67e92763d85 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is 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.
transform_matrix_offset_center in 11 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 3e773c6c5bc796d4 · report fixture: signature matrix:ndarray/2/float, x:int/0/int, y:int/0/int · returned ndarray · level recorded 2026-09-22

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.

6 assemblies on this paper: 6 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for RandAugment (graph method: RandAugment). 20 bricks; individually on a fixture: 19 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 17 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. RandAugment entry · level 1 · ran · eb475b4fcf7d8891
  2. augment_list data_transform · level 1 · ran · b6eb3433772b9aac
  3. AutoContrast data_transform · level 1 · ran · our draft was wrong · 4a0ac9d611e018bc
  4. Contrast data_transform · level 1 · ran; the contract check could not run (RAISES) · 35f5a6d3913e6b0e
  5. CutoutAbs helper · level 1 · ran; the contract check could not run (RAISES) · 03ecbd868107e6f7
  6. Equalize data_transform · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  7. Invert data_transform · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  8. Posterize data_transform · level 1 · ran · our draft was wrong · 19b3cb2d9f27fcdb
  9. Rotate data_transform · level 1 · ran; the contract check could not run (RAISES) · b22d322fc26595bc
  10. Sharpness data_transform · level 1 · ran; the contract check could not run (RAISES) · e1ccc58bf76a30b9
  11. ShearX data_transform · level 1 · ran; the contract check could not run (RAISES) · 815f704e5efd8345
  12. ShearY data_transform · level 1 · ran; the contract check could not run (RAISES) · f5e3179cafd9393a
  13. Solarize data_transform · level 1 · ran; the contract check could not run (RAISES) · 70eab251c4b2bce2
  14. SolarizeAdd helper · level 0 · unverified · 1c3be67e92763d85
  15. ToBLUR helper · level 1 · ran · our draft was wrong · e74342905c295c87
  16. ToCONTOUR helper · level 1 · ran · our draft was wrong · c28a72552d33774e
  17. ToEDGES helper · level 1 · ran · our draft was wrong · 6479c2b0e4d54d6a
  18. ToEMBOSS helper · level 1 · ran · our draft was wrong · ce08e08f28dfcee7
  19. TranslateXabs helper · level 1 · ran; the contract check could not run (RAISES) · d6e5e2e212d3e912
  20. TranslateYabs helper · level 1 · ran; the contract check could not run (RAISES) · 52872165441774c7

harvested Assembly for RandAugment (graph method: RandAugment). 17 bricks; individually on a fixture: 15 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; 15 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. RandAugment entry · level 0 · unverified · ad7a01616e026f1c
  2. autocontrast data_transform · level 1 · ran · our draft was wrong · 033f4c7eebc4b8bc
  3. brightness data_transform · level 1 · ran; the contract check could not run (RAISES) · c853710460b412e7
  4. color data_transform · level 1 · ran; the contract check could not run (RAISES) · 5f1efa6a7f09bf92
  5. contrast data_transform · level 1 · ran; the contract check could not run (RAISES) · 74223e0d5db8f6dc
  6. cutout data_transform · level 1 · ran; the contract check could not run (RAISES) · a07328daac80e5d4
  7. equalize data_transform · level 1 · ran · our draft was wrong · 6f465d3353435748
  8. invert data_transform · level 1 · ran · our draft was wrong · b794fd0b35eea322
  9. posterize data_transform · level 1 · ran · our draft was wrong · ac724bc0e98f3cda
  10. rotate data_transform · level 1 · ran; the contract check could not run (RAISES) · 6d903cf9b58e8ce3
  11. sharpness data_transform · level 1 · ran; the contract check could not run (RAISES) · cbbf595da3dbb1fd
  12. shearx data_transform · level 1 · ran; the contract check could not run (RAISES) · 472154b113f3c670
  13. sheary data_transform · level 1 · ran; the contract check could not run (RAISES) · 9cc62c9a79622659
  14. solarize data_transform · level 1 · ran; the contract check could not run (RAISES) · b8a2aca46dc33d3f
  15. solarizeadd data_transform · level 0 · unverified · 3931a647e47e6c9e
  16. translatex data_transform · level 1 · ran; the contract check could not run (RAISES) · 845982ca54304048
  17. translatey data_transform · level 1 · ran; the contract check could not run (RAISES) · 2c8f458ee8d12c14

harvested Assembly for RandAugment (graph method: RandAugment). 16 bricks; individually on a fixture: 16 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 13 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. RandAugment entry · level 1 · ran · e097e00c2974ac62
  2. augment_list data_transform · level 1 · ran · fa05edca4ee502d1
  3. AutoContrast data_transform · level 1 · ran · our draft was wrong · 4a0ac9d611e018bc
  4. Brightness data_transform · level 1 · ran; the contract check could not run · 993134d3c95bcf92
  5. Color data_transform · level 1 · ran; the contract check could not run · ccaa14b841bf44dc
  6. Equalize data_transform · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  7. Identity data_transform · level 1 · ran · violated contract · 08f47bae89750cac
  8. Invert data_transform · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  9. Posterize data_transform · level 1 · ran; the contract check could not run · d2a9bd74240b6944
  10. Rotate data_transform · level 1 · ran; the contract check could not run (RAISES) · b22d322fc26595bc
  11. Sharpness data_transform · level 1 · ran; the contract check could not run (RAISES) · e1ccc58bf76a30b9
  12. ShearX data_transform · level 1 · ran; the contract check could not run (RAISES) · 815f704e5efd8345
  13. ShearY data_transform · level 1 · ran; the contract check could not run (RAISES) · f5e3179cafd9393a
  14. Solarize data_transform · level 1 · ran; the contract check could not run (RAISES) · 70eab251c4b2bce2
  15. TranslateX data_transform · level 1 · ran; the contract check could not run (RAISES) · b2893a9a2ac1188f
  16. TranslateY data_transform · level 1 · ran; the contract check could not run (RAISES) · e3a2ec04026a49e8

harvested Assembly for RandAugment (graph method: RandAugment). 16 bricks; individually on a fixture: 16 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 13 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. RandAugment entry · level 1 · ran · cd8cce1f7b2b9e61
  2. augment_list data_transform · level 1 · ran · 0e2bfdf3982286ac
  3. AutoContrast data_transform · level 1 · ran · our draft was wrong · 4a0ac9d611e018bc
  4. Brightness data_transform · level 1 · ran; the contract check could not run · 993134d3c95bcf92
  5. Color data_transform · level 1 · ran; the contract check could not run · ccaa14b841bf44dc
  6. Equalize data_transform · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  7. Identity data_transform · level 1 · ran · violated contract · 08f47bae89750cac
  8. Invert data_transform · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  9. Posterize data_transform · level 1 · ran; the contract check could not run · d2a9bd74240b6944
  10. Rotate data_transform · level 1 · ran; the contract check could not run (RAISES) · b22d322fc26595bc
  11. Sharpness data_transform · level 1 · ran; the contract check could not run (RAISES) · e1ccc58bf76a30b9
  12. ShearX data_transform · level 1 · ran · our draft was wrong · 9846307204b08173
  13. ShearY data_transform · level 1 · ran · our draft was wrong · 109155544d6d2c48
  14. Solarize data_transform · level 1 · ran; the contract check could not run (RAISES) · 70eab251c4b2bce2
  15. TranslateX data_transform · level 1 · ran · our draft was wrong · f03d112eee854337
  16. TranslateY data_transform · level 1 · ran · our draft was wrong · e02e6b30e0c6b0ab

harvested Assembly for RandAugment (graph method: RandAugment). 17 bricks; individually on a fixture: 15 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; 15 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. apply_policy entry · level 0 · unverified · 89a74c24e1285658
  2. auto_contrast data_transform · level 1 · ran · our draft was wrong · 5ea03e170ec307dd
  3. brightness data_transform · level 1 · ran · our draft was wrong · 32a7da0ae8a21668
  4. color data_transform · level 1 · ran · our draft was wrong · 747a0d64c7ffa9e5
  5. contrast data_transform · level 1 · ran · our draft was wrong · 6d3fa2f36220efed
  6. cutout data_transform · level 0 · unverified · 93e2ff77da69661e
  7. equalize data_transform · level 1 · ran · our draft was wrong · 51eba7748cab33ee
  8. invert data_transform · level 1 · ran · our draft was wrong · a14dd4fa2af8e72e
  9. posterize data_transform · level 1 · ran · our draft was wrong · c2b9e317cc24e2a5
  10. rotate data_transform · level 1 · ran; the contract check could not run (RAISES) · 8d1db612602ab793
  11. sharpness data_transform · level 1 · ran · our draft was wrong · 3f5e624979a30a88
  12. shear_x data_transform · level 1 · ran; the contract check could not run (RAISES) · 7fad25ebc151a21a
  13. shear_y data_transform · level 1 · ran; the contract check could not run (RAISES) · eb627b1078fe24a3
  14. solarize data_transform · level 1 · ran · our draft was wrong · f5999a1ee8824e22
  15. transform_matrix_offset_center helper · level 1 · ran · our draft was wrong · 3e773c6c5bc796d4
  16. translate_x data_transform · level 1 · ran; the contract check could not run (RAISES) · 9c2425c71cab36a2
  17. translate_y data_transform · level 1 · ran; the contract check could not run (RAISES) · bd8449369ce2815d

harvested Assembly for RandAugment (graph method: RandAugment). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. BatchRandAugment entry · level 0 · unverified · 2f969dec47d024ae
  2. kornia_list data_transform · level 0 · unverified · a56a697ec3f193c1

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="1909.13719") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationDomain GeneralizationImage ClassificationObject Detectionimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Data Augmentation ImageNet ResNet-50 (RA) Accuracy (%) 77.6 #14 of 17 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B7 (randaug) Accuracy - All Images 45 #17 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B7 (randaug) Accuracy - Clean Images 48.7 #17 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B7 (randaug) Accuracy - Corrupted Images 38.9 #17 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B5 (randaug) Accuracy - All Images 42.1 #25 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B5 (randaug) Accuracy - Clean Images 47.3 #25 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B5 (randaug) Accuracy - Corrupted Images 35.5 #25 of 90 Archive leaderboard report
Image Classification ImageNet EfficientNet-B8 (RandAugment) Top 1 Accuracy 85.4% #227 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNet-B7 (RandAugment) Number of params 66M #269 of 1060 Archive leaderboard report
Image Classification ImageNet EfficientNet-B7 (RandAugment) Top 1 Accuracy 85% #269 of 1060 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 ConvolutionAutoAugmentAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterConvolutionCosine AnnealingCutoutDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetFPNFocal LossGlobal Average PoolingInverted Residual BlockKaiming InitializationLSTMMax PoolingPointwise ConvolutionRMSPropRandAugmentRandom Horizontal FlipRandom Resized CropReLUResidual BlockResidual ConnectionRetinaNetSGD with MomentumShakeDropSigmoid ActivationSqueeze-and-Excitation BlockTanh ActivationWeight DecayWide Residual BlockWideResNet

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