Papers › AutoAugment: Learning Augmentation Policies from Data
AutoAugment: Learning Augmentation Policies from Data
Ekin D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, Quoc V. Le
Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch. A sub-policy consists of two operations, each operation being an image processing function such as translation, rotation, or shearing, and the probabilities and magnitudes with which the functions are applied. We use a search algorithm to find the best policy such that the neural network yields the highest validation accuracy on a target dataset. Our method achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, SVHN, and ImageNet (without additional data). On ImageNet, we attain a Top-1 accuracy of 83.5% which is 0.4% better than the previous record of 83.1%. On CIFAR-10, we achieve an error rate of 1.5%, which is 0.6% better than the previous state-of-the-art. Augmentation policies we find are transferable between datasets. The policy learned on ImageNet transfers well to achieve significant improvements on other datasets, such as Oxford Flowers, Caltech-101, Oxford-IIT Pets, FGVC Aircraft, and Stanford Cars.
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):
get_harvested_code_for_paper(arxiv_id="1805.09501")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1805.09501", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1805.09501")
Code
No sample from the archive's official repository (tensorflow/models) is linked to this paper; the 43 samples below come from 7 community repositories. Syntology harvested code from tensorflow/models for 4 other papers.
tensorflow/models: Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.
Syntology 43 code samples harvested from 7 repositories linked to this paper: 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: community (archive-listed): 43 samples from 7 repositories, 25 ran (22 with no instrument failure; 3 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 12 of its repositories that Syntology harvested for other papers:
- tensorflow/models, official repository: harvested for 4 other papers, listed under the repository
- YaCpotato/B4ResearchDeepaugment, community (archive-listed): harvested for another paper, listed under the repository
- etetteh/sota-data-augmentation-and-optimizers, community (archive-listed): harvested for 2 other papers, listed under the repository
- ilyak93/GAIN-pytorch, community (archive-listed): harvested for another paper, listed under the repository
- lyxxn0414/test-data-generation, community (archive-listed): harvested for another paper, listed under the repository
- mingsun-tse/good-da-in-kd, community (archive-listed): harvested for 3 other papers, listed under the repository
- ofa-sys/chinese-clip, community (archive-listed): harvested for another paper, listed under the repository
- open-mmlab/mmpretrain, community (archive-listed): harvested for another paper, listed under the repository
- tensorflow/tpu, community (archive-listed): harvested for another paper, listed under the repository
- zhanghang1989/fast-autoaug-torch, community (archive-listed): harvested for another paper, listed under the repository
- pytorch/vision, community (archive-listed): harvested for 10 other papers, listed under the repository
- wangermeng2021/FastClassification, community (archive-listed): harvested for 2 other papers, listed under the repository
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.
33 repositories listed; official and paper-mentioned ones first.
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
43 samples harvested: 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 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.
Licence: 4 of the 43 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 7 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.
d7b9dce3fe1c3682 · report
fixture: signature models:callable/0/?, optim:str/0/str, lr:float/0/float, weight_decay:float/0/float, momentum:float/0/float, sgd_dampening:int/0/int, sgd_nesterov:bool/0/bool, rmsprop_alpha:float/0/float, adam_beta1:float/0/float, adam_beta2:float/0/float, staged_lr:bool/0/bool, new_layers:str/0/str, base_lr_mult:float/0/float · returned Adam · level recorded 2026-09-26 90ac063c815a1d9d · report
fixture: returned ndarray · level recorded 2026-09-26 82f35d7c062474b2 · report
fixture: signature in_dim:int/0/int, out_dim:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, norm:callable/0/?, relu:callable/0/? · returned Sequential · level recorded 2026-09-26 1e9f2436aa92ae9c · report
fixture: signature distmat:ndarray/2/float, q_pids:ndarray/1/int, g_pids:ndarray/1/int, q_camids:ndarray/1/int, g_camids:ndarray/1/int, max_rank:int/0/int · returned tuple · level recorded 2026-09-26 a355d3e47a6679b6 · report
fixture: signature distmat:ndarray/2/float, q_pids:ndarray/1/int, g_pids:ndarray/1/int, q_camids:ndarray/1/int, g_camids:ndarray/1/int, max_rank:int/0/int · returned tuple · level recorded 2026-09-26 99f281b515b56572 · report
fixture: signature distmat:ndarray/2/float, q_pids:ndarray/1/int, g_pids:ndarray/1/int, q_camids:ndarray/1/int, g_camids:ndarray/1/int, max_rank:int/0/int, use_metric_cuhk03:bool/0/bool · returned tuple · level recorded 2026-09-26 a610e67edff490e6 · report
fixture: signature initial_rank:ndarray/2/int, i:int/0/int, k1:int/0/int · returned ndarray · level recorded 2026-09-24 7aa201aa3874fe38 · report
fixture: signature q_g_dist:ndarray/2/float, q_q_dist:ndarray/2/float, g_g_dist:ndarray/2/float, k1:int/0/int, k2:int/0/int, lambda_value:float/0/float · returned ndarray · level recorded 2026-09-26 f295b8050ce2a4f1 · report
fixture: signature x:Tensor/2/float · returned SwigPyObject · level recorded 2026-09-25 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket openunreid/core/metrics/accuracy.py unverified MIT (permissive) ·
6567404952193dea · report
1ec9335c14b72b00 · report
4b1b3ea8808ebb91 · report
3db04fbfca62bfd0 · report
6e090295d64d8710 · report
0359516a2e2ae26c · report
02d028e6867abbb5 · report
434ddd5d59a07613 · report
7abb26d9e95eace9 · report
6fe5cdb6dc4e08be · report
78ca4879f13cc9d5 · report
892aeccb03c9a237 · report
53613a740588d619 · report
fixture: signature img:Image/0/?, magnitude:int/0/int · returned Image · level recorded 2026-09-22 3e773c6c5bc796d4 · report
fixture: signature matrix:ndarray/2/float, x:int/0/int, y:int/0/int · returned ndarray · level recorded 2026-09-22 250ec7daec9a09f3 · report
fixture: signature input_shape:tuple/1/int, num_classes:int/0/int · returned Functional · level recorded 2026-09-26 02d4d29f63aa94f2 · report
fixture: signature level:int/0/int, maxval:float/0/float, minval:float/0/float · returned float · level recorded 2026-09-26 d9e70dca8d829825 · report
fixture: signature level:int/0/int, maxval:int/0/int, minval:int/0/int · returned int · level recorded 2026-09-26 census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket deepaugment/augmenter.py ran fingerprinted MIT (permissive) ·
92ae1c2343aa2f75 · report
fixture: signature X:ndarray/2/float · returned ndarray · level recorded 2026-09-26 b02a7aace3f1f0f2 · report
fixture: signature path:str/0/str · returned str · level recorded 2026-09-26 census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket deepaugment/augmenter.py ran fingerprinted MIT (permissive) ·
034fc6cedc751d69 · report
fixture: signature X:ndarray/3/float · returned ndarray · level recorded 2026-09-26 6e1198a9c8c47438 · report
fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-25 0f4de8752a1072ea · report
fixture: signature img:ndarray/3/float, amount:int/0/int · returned ndarray · level recorded 2026-09-26 93204f7c934e37f7 · report
fixture: signature file_path:str/0/str · returned Logger · level recorded 2026-09-26 e743627634484e6d · report
fixture: signature model:callable/0/? · returned float64 · level recorded 2026-09-24 ae11f865c7d70581 · report
fixture: signature alpha:callable/0/?, k:int/0/int · returned list · level recorded 2026-09-26 fdfb2f691ca67d7f · report
2c98f33a195f457b · report
fixture: signature image:ndarray/3/int · returned Image · level recorded 2026-09-22 702d7cf93651bbf8 · report
fixture: signature image:Image/0/? · returned ndarray · level recorded 2026-09-22 f8a38db0674e2431 · report
fixture: signature dataset:SimpleDataset/0/?, cvs:list/1/tuple · returned tuple · level recorded 2026-09-22 6f457a08830581a5 · report
Tasks
Results from the paper archive 2025-07-28
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
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