Papers › Fast AutoAugment
Fast AutoAugment
Sungbin Lim, Ildoo Kim, Taesup Kim, Chiheon Kim, Sungwoong Kim
Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has significantly enhanced performances on many image recognition tasks. However, its search method requires thousands of GPU hours even for a relatively small dataset. In this paper, we propose an algorithm called Fast AutoAugment that finds effective augmentation policies via a more efficient search strategy based on density matching. In comparison to AutoAugment, the proposed algorithm speeds up the search time by orders of magnitude while achieves comparable performances on image recognition tasks with various models and datasets including CIFAR-10, CIFAR-100, SVHN, and ImageNet.
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="1905.00397")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1905.00397", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1905.00397")
Code
Syntology 40 code samples harvested from 7 repositories linked to this paper: 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. Where Syntology's instrument failed: 4 where our contract draft was wrong; 12 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 10 samples from 1 repository, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 30 samples from 6 repositories, 28 ran (14 with no instrument failure; 14 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 3 of its repositories that Syntology harvested for other papers:
- cfld/amdim, community (archive-listed): harvested for another paper, listed under the repository
- philip-bachman/amdim-public, 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
Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 37 samples that ran has no recorded date.
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
40 samples harvested: 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. “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: 7 of the 40 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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.
fac5364e2f53c6db · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded 03a0be4fb7381bd2 · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22 40d3c39a403ae1f7 · report
fixture: signature level:int/0/int, maxval:float/0/float · returned float · level recorded 2026-09-24 6066adc7a58afde6 · report
fixture: signature name:str/0/str, level:int/0/int · returned Logger · level recorded 2026-09-25 7900a3a6deef908b · report
fixture: signature level:int/0/int, maxval:int/0/int · returned int · level recorded 2026-09-24 8b2b8ba48892e73e · report
fixture: signature data:Tensor/2/float, targets:Tensor/1/int, alpha:float/0/float · returned tuple · level recorded 2026-09-25 10d196b211843339 · report
fixture: signature root:str/0/str · returned tuple · level recorded 2026-09-25 97bfaa2cce837d67 · report
fixture: signature devkit_root:str/0/str, path:str/0/str, filename:str/0/str · returned tuple · level recorded 2026-09-25 e7825a1705689714 · report
fixture: signature devkit_root:str/0/str, path:str/0/str, filename:str/0/str · returned list · level recorded 2026-09-25 census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket FastAutoAugment/metrics.py unverified MIT (permissive) ·
3ccb35170e45f022 · report
a43ccb0a81208bab · report
fixture: returned list · level recorded 2026-09-22 75171b0fbf864dbb · report
fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22 9c6958943035b251 · report
fixture: returned RandAugment · level recorded 2026-09-22 5d568852c0fdc6a3 · report
fixture: returned list · 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
b92936d1f2ac3e6c · report
fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22 008c64b77c4ae4c9 · report
fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22 ab50d5bbcf589623 · report
fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22 0a6d90cf17a6a7b6 · report
fixture: signature m:callable/0/?, x:tuple/1/Tensor, y:Tensor/4/float · returned int · level recorded 2026-09-24 2495aa8db734b762 · report
fixture: signature m:callable/0/?, x:tuple/1/Tensor, y:Tensor/4/float · returned int · level recorded 2026-09-24 8adf833ce8491ae7 · report
fixture: signature m:callable/0/?, x:tuple/1/Tensor, y:Tensor/2/float · returned int · level recorded 2026-09-24 5d3725d10f387239 · report
fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24 500151731fe0c778 · report
fixture: signature scheduler:callable/0/?, init_scale:float/0/float · returned function · level recorded 2026-09-24 fd8ab66e1567e6f2 · report
fixture: signature scheduler:callable/0/? · returned function · level recorded 2026-09-24 58895526cd27ed71 · report
fixture: signature name:str/0/str, stream:StringIO/0/? · returned Logger · level recorded 2026-09-24 305d5112606704d9 · report
fixture: signature height:int/0/int, width:int/0/int · returned function · level recorded 2026-09-24 58be042029debe2d · report
fixture: signature is_random_flip:bool/0/bool · returned function · level recorded 2026-09-24 5f37303469d04cab · report
fixture: signature scheduler:callable/0/?, warm_up_epoch:int/0/int, multiplier:float/0/float · returned function · level recorded 2026-09-24 993134d3c95bcf92 · report
fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22 ccaa14b841bf44dc · report
fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22 f90119cfdd38ef56 · report
fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22 d2a9bd74240b6944 · report
fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22 067680c1cc9f4b97 · report
fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22 b1fc55be13be06e7 · report
fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22 d4b73cc9fa9b08ae · report
fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22 15ceb820d17f0a5c · report
fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22 1ca02113ff95139e · report
fixture: returned UniformAugment · level recorded 2026-09-22 b1cd4e4b4bba7f8c · report
fixture: signature for_autoaug:bool/0/bool · returned list · 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.
3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
3 sibling assemblies for Fast AutoAugment (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Fast AutoAugment (graph method: Fast AutoAugment). 21 bricks; individually on a fixture: 21 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 20 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- UniformAugment entry · level 1 · ran ·
1ca02113ff95139e - augment_list data_transform · level 1 · ran · our draft was wrong ·
b1cd4e4b4bba7f8c - AutoContrast helper · level 1 · ran · our draft was wrong ·
4a0ac9d611e018bc - Brightness helper · level 1 · ran; the contract check could not run (RAISES) ·
993134d3c95bcf92 - Color helper · level 1 · ran; the contract check could not run (RAISES) ·
ccaa14b841bf44dc - Contrast helper · level 1 · ran; the contract check could not run ·
35f5a6d3913e6b0e - Cutout helper · level 1 · ran; the contract check could not run (RAISES) ·
f90119cfdd38ef56 - CutoutAbs helper · level 1 · ran; the contract check could not run ·
03ecbd868107e6f7 - Equalize helper · level 1 · ran · our draft was wrong ·
4befb1744e90f3a1 - Invert helper · level 1 · ran · our draft was wrong ·
f5f0bf976dfcf068 - Posterize helper · level 1 · ran; the contract check could not run (RAISES) ·
d2a9bd74240b6944 - Posterize2 helper · level 1 · ran; the contract check could not run (RAISES) ·
067680c1cc9f4b97 - Rotate helper · level 1 · ran · our draft was wrong ·
21c6427b09f14649 - Sharpness helper · level 1 · ran; the contract check could not run ·
e1ccc58bf76a30b9 - ShearX helper · level 1 · ran; the contract check could not run (RAISES) ·
b92936d1f2ac3e6c - ShearY helper · level 1 · ran; the contract check could not run (RAISES) ·
008c64b77c4ae4c9 - Solarize helper · level 1 · ran; the contract check could not run ·
70eab251c4b2bce2 - TranslateX helper · level 1 · ran; the contract check could not run (RAISES) ·
ab50d5bbcf589623 - TranslateXAbs helper · level 1 · ran; the contract check could not run (RAISES) ·
b1fc55be13be06e7 - TranslateY helper · level 1 · ran; the contract check could not run (RAISES) ·
d4b73cc9fa9b08ae - TranslateYAbs helper · level 1 · ran; the contract check could not run (RAISES) ·
15ceb820d17f0a5c
harvested Assembly for Fast AutoAugment (graph method: Fast AutoAugment). 18 bricks; individually on a fixture: 17 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 15 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- RandAugment entry · level 1 · ran ·
9c6958943035b251 - augment_list data_transform · level 1 · ran ·
5d568852c0fdc6a3 - AutoContrast data_transform · level 1 · ran · our draft was wrong ·
4a0ac9d611e018bc - Brightness data_transform · level 1 · ran; the contract check could not run (RAISES) ·
993134d3c95bcf92 - Color data_transform · level 1 · ran; the contract check could not run (RAISES) ·
ccaa14b841bf44dc - Contrast data_transform · level 1 · ran; the contract check could not run ·
35f5a6d3913e6b0e - CutoutAbs helper · level 1 · ran; the contract check could not run ·
03ecbd868107e6f7 - Equalize data_transform · level 1 · ran · our draft was wrong ·
4befb1744e90f3a1 - Invert data_transform · level 1 · ran · our draft was wrong ·
f5f0bf976dfcf068 - Posterize data_transform · level 1 · ran · our draft was wrong ·
75171b0fbf864dbb - Rotate data_transform · level 1 · ran; the contract check could not run ·
b22d322fc26595bc - Sharpness data_transform · level 1 · ran; the contract check could not run ·
e1ccc58bf76a30b9 - ShearX data_transform · level 1 · ran; the contract check could not run ·
815f704e5efd8345 - ShearY data_transform · level 1 · ran; the contract check could not run ·
f5e3179cafd9393a - Solarize data_transform · level 1 · ran; the contract check could not run ·
70eab251c4b2bce2 - SolarizeAdd helper · level 0 · unverified ·
fcce9b35a12cd32c - TranslateXabs helper · level 1 · ran; the contract check could not run ·
d6e5e2e212d3e912 - TranslateYabs helper · level 1 · ran; the contract check could not run ·
52872165441774c7
harvested Assembly for Fast AutoAugment (graph method: Fast AutoAugment). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 3 siblings
- fa_reduced_cifar10 entry · level 1 · ran ·
a43ccb0a81208bab
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="1905.00397") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Data Augmentation | ImageNet | ResNet-200 (Fast AA) | Accuracy (%) | 80.6 | #4 of 17 | Archive leaderboard | report |
| Data Augmentation | ImageNet | ResNet-50 (Fast AA) | Accuracy (%) | 77.6 | #13 of 17 | Archive leaderboard | report |
| Image Classification | CIFAR-10 | PyramidNet+ShakeDrop (Fast AA) | Percentage correct | 98.3 | #46 of 265 | Archive leaderboard | report |
| Image Classification | CIFAR-100 | PyramidNet+ShakeDrop (Fast AA) | Percentage correct | 88.3 | #38 of 211 | Archive leaderboard | report |
| Image Classification | ImageNet | ResNet-200 (Fast AA) | Top 1 Accuracy | 80.6% | #691 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ResNet-50 (Fast AA) | Top 1 Accuracy | 77.6% | #867 of 1060 | Archive leaderboard | report |
| Image Classification | SVHN | Wide-ResNet-28-10 (Fast AA) | Percentage error | 1.1 | #2 of 62 | 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: Fast AutoAugment
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