Papers › Fast AutoAugment

Fast AutoAugment

1 May 2019NeurIPS 2019 12arXiv:1905.00397archive 2025-07-28

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.

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 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:

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.

kakaobrain/fast-autoaugment officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 9 ran (2 instrument-failed) · 1 unverified report
Ching-Chen-Wang/EfficientNet-eLite mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cfld/amdim mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Representations by Maximizing Mutual Information Across Views (arXiv:1906.00910; 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, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
ildoonet/pytorch-randaugment mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (1 instrument-failed) · 1 unverified report
junkwhinger/fastautoaugment_jsh mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
kakaobrain/autoclint mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
philip-bachman/amdim-public mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Representations by Maximizing Mutual Information Across Views (arXiv:1906.00910; 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, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
songyadong106/111 mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 10 ran (0 instrument-failed) · 0 unverified report
tgilewicz/uniformaugment mentioned on GitHubpytorchSyntology: 10 samples, 10 ran (9 instrument-failed) · 0 unverified report
zhanghang1989/fast-autoaug-torch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 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); nothing checks that they implement this paper's method. report
NoamRosenberg/fast-autoaugment-on-a-single-gpu pytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

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.

2ran · honoured contract
4ran · our draft was wrong
12ran; the contract check could not run
19ran
3unverified

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.

kakaobrain/fast-autoaugment official repository 10 samples, 9 ran (2 instrument-failed) · 1 unverified
conv3x3 in 1,376 papers FastAutoAugment/networks/resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 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
conv3x3 in 1,376 papers FastAutoAugment/networks/pyramidnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 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
float_parameter in 36 papers archive.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 40d3c39a403ae1f7 · report fixture: signature level:int/0/int, maxval:float/0/float · returned float · level recorded 2026-09-24
get_logger in 383 papers FastAutoAugment/common.py ran MIT (permissive) · 6066adc7a58afde6 · report fixture: signature name:str/0/str, level:int/0/int · returned Logger · level recorded 2026-09-25
int_parameter in 35 papers archive.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 7900a3a6deef908b · report fixture: signature level:int/0/int, maxval:int/0/int · returned int · level recorded 2026-09-24
mixup in 28 papers FastAutoAugment/aug_mixup.py ran fingerprinted MIT (permissive) · 8b2b8ba48892e73e · report fixture: signature data:Tensor/2/float, targets:Tensor/1/int, alpha:float/0/float · returned tuple · level recorded 2026-09-25
parse_devkit in 5 papers FastAutoAugment/imagenet.py ran MIT (permissive) · 10d196b211843339 · report fixture: signature root:str/0/str · returned tuple · level recorded 2026-09-25
parse_meta in 7 papers FastAutoAugment/imagenet.py ran MIT (permissive) · 97bfaa2cce837d67 · report fixture: signature devkit_root:str/0/str, path:str/0/str, filename:str/0/str · returned tuple · level recorded 2026-09-25
parse_val_groundtruth FastAutoAugment/imagenet.py ran MIT (permissive) · e7825a1705689714 · report fixture: signature devkit_root:str/0/str, path:str/0/str, filename:str/0/str · returned list · level recorded 2026-09-25
Ching-Chen-Wang/EfficientNet-eLite community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
fa_reduced_cifar10 EfficientNet-eLite/archive.py ran · metamorphic tier: deterministic no licence file found · pointer only · a43ccb0a81208bab · report fixture: returned list · level recorded 2026-09-22
ildoonet/pytorch-randaugment community (archive-listed) 4 samples, 3 ran (1 instrument-failed) · 1 unverified
Posterize RandAugment/augmentations.py ran · our draft was wrong MIT (permissive) · 75171b0fbf864dbb · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
RandAugment RandAugment/augmentations.py ran MIT (permissive) · 9c6958943035b251 · report fixture: returned RandAugment · level recorded 2026-09-22
augment_list RandAugment/augmentations.py ran MIT (permissive) · 5d568852c0fdc6a3 · report fixture: returned list · level recorded 2026-09-22
SolarizeAdd RandAugment/augmentations.py unverified MIT (permissive) · fcce9b35a12cd32c · report
junkwhinger/fastautoaugment_jsh community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
split_dataset_train search_fastautoaugment.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) licence of this copy not recorded · f8a38db0674e2431 · report fixture: signature dataset:SimpleDataset/0/?, cvs:list/1/tuple · returned tuple · level recorded 2026-09-22
generate_cv_sets search_fastautoaugment.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 6f457a08830581a5 · report
kakaobrain/autoclint community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
ShearX in 14 papers skeleton/data/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · b92936d1f2ac3e6c · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ShearY in 14 papers skeleton/data/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 008c64b77c4ae4c9 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
TranslateX in 13 papers skeleton/data/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · ab50d5bbcf589623 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
songyadong106/111 community (archive-listed) 10 samples, 10 ran (0 instrument-failed) · 0 unverified
count_bn2d skeleton/nn/modules/profile.py ran Apache-2.0 (permissive) · 0a6d90cf17a6a7b6 · report fixture: signature m:callable/0/?, x:tuple/1/Tensor, y:Tensor/4/float · returned int · level recorded 2026-09-24
count_conv2d skeleton/nn/modules/profile.py ran Apache-2.0 (permissive) · 2495aa8db734b762 · report fixture: signature m:callable/0/?, x:tuple/1/Tensor, y:Tensor/4/float · returned int · level recorded 2026-09-24
count_relu skeleton/nn/modules/profile.py ran Apache-2.0 (permissive) · 8adf833ce8491ae7 · report fixture: signature m:callable/0/?, x:tuple/1/Tensor, y:Tensor/2/float · returned int · level recorded 2026-09-24
decorator_tuple_to_args skeleton/nn/modules/wrappers.py ran Apache-2.0 (permissive) · 5d3725d10f387239 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
get_change_scale skeleton/optim/scheduler.py ran Apache-2.0 (permissive) · 500151731fe0c778 · report fixture: signature scheduler:callable/0/?, init_scale:float/0/float · returned function · level recorded 2026-09-24
get_discrete_epoch skeleton/optim/scheduler.py ran Apache-2.0 (permissive) · fd8ab66e1567e6f2 · report fixture: signature scheduler:callable/0/? · returned function · level recorded 2026-09-24
get_logger in 383 papers skeleton/projects/others.py ran Apache-2.0 (permissive) · 58895526cd27ed71 · report fixture: signature name:str/0/str, stream:StringIO/0/? · returned Logger · level recorded 2026-09-24
get_tf_resize skeleton/projects/others.py ran Apache-2.0 (permissive) · 305d5112606704d9 · report fixture: signature height:int/0/int, width:int/0/int · returned function · level recorded 2026-09-24
get_tf_to_tensor skeleton/projects/others.py ran Apache-2.0 (permissive) · 58be042029debe2d · report fixture: signature is_random_flip:bool/0/bool · returned function · level recorded 2026-09-24
gradual_warm_up skeleton/optim/scheduler.py ran Apache-2.0 (permissive) · 5f37303469d04cab · report fixture: signature scheduler:callable/0/?, warm_up_epoch:int/0/int, multiplier:float/0/float · returned function · level recorded 2026-09-24
tgilewicz/uniformaugment community (archive-listed) 10 samples, 10 ran (9 instrument-failed) · 0 unverified
Brightness in 31 papers UniformAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 993134d3c95bcf92 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Color in 29 papers UniformAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · ccaa14b841bf44dc · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Cutout in 6 papers UniformAugment/augmentations.py ran; the contract check could not run (RAISES) MIT (permissive) · f90119cfdd38ef56 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
Posterize UniformAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · d2a9bd74240b6944 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
Posterize2 UniformAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 067680c1cc9f4b97 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
TranslateXAbs UniformAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · b1fc55be13be06e7 · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
TranslateY UniformAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · d4b73cc9fa9b08ae · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
TranslateYAbs UniformAugment/augmentations.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 15ceb820d17f0a5c · report fixture: signature img:Image/0/?, v:int/0/int · returned Image · level recorded 2026-09-22
UniformAugment UniformAugment/augmentations.py ran MIT (permissive) · 1ca02113ff95139e · report fixture: returned UniformAugment · level recorded 2026-09-22
augment_list UniformAugment/augmentations.py ran · our draft was wrong fingerprinted MIT (permissive) · 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

  1. UniformAugment entry · level 1 · ran · 1ca02113ff95139e
  2. augment_list data_transform · level 1 · ran · our draft was wrong · b1cd4e4b4bba7f8c
  3. AutoContrast helper · level 1 · ran · our draft was wrong · 4a0ac9d611e018bc
  4. Brightness helper · level 1 · ran; the contract check could not run (RAISES) · 993134d3c95bcf92
  5. Color helper · level 1 · ran; the contract check could not run (RAISES) · ccaa14b841bf44dc
  6. Contrast helper · level 1 · ran; the contract check could not run · 35f5a6d3913e6b0e
  7. Cutout helper · level 1 · ran; the contract check could not run (RAISES) · f90119cfdd38ef56
  8. CutoutAbs helper · level 1 · ran; the contract check could not run · 03ecbd868107e6f7
  9. Equalize helper · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  10. Invert helper · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  11. Posterize helper · level 1 · ran; the contract check could not run (RAISES) · d2a9bd74240b6944
  12. Posterize2 helper · level 1 · ran; the contract check could not run (RAISES) · 067680c1cc9f4b97
  13. Rotate helper · level 1 · ran · our draft was wrong · 21c6427b09f14649
  14. Sharpness helper · level 1 · ran; the contract check could not run · e1ccc58bf76a30b9
  15. ShearX helper · level 1 · ran; the contract check could not run (RAISES) · b92936d1f2ac3e6c
  16. ShearY helper · level 1 · ran; the contract check could not run (RAISES) · 008c64b77c4ae4c9
  17. Solarize helper · level 1 · ran; the contract check could not run · 70eab251c4b2bce2
  18. TranslateX helper · level 1 · ran; the contract check could not run (RAISES) · ab50d5bbcf589623
  19. TranslateXAbs helper · level 1 · ran; the contract check could not run (RAISES) · b1fc55be13be06e7
  20. TranslateY helper · level 1 · ran; the contract check could not run (RAISES) · d4b73cc9fa9b08ae
  21. 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

  1. RandAugment entry · level 1 · ran · 9c6958943035b251
  2. augment_list data_transform · level 1 · ran · 5d568852c0fdc6a3
  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 (RAISES) · 993134d3c95bcf92
  5. Color data_transform · level 1 · ran; the contract check could not run (RAISES) · ccaa14b841bf44dc
  6. Contrast data_transform · level 1 · ran; the contract check could not run · 35f5a6d3913e6b0e
  7. CutoutAbs helper · level 1 · ran; the contract check could not run · 03ecbd868107e6f7
  8. Equalize data_transform · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  9. Invert data_transform · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  10. Posterize data_transform · level 1 · ran · our draft was wrong · 75171b0fbf864dbb
  11. Rotate data_transform · level 1 · ran; the contract check could not run · b22d322fc26595bc
  12. Sharpness data_transform · level 1 · ran; the contract check could not run · e1ccc58bf76a30b9
  13. ShearX data_transform · level 1 · ran; the contract check could not run · 815f704e5efd8345
  14. ShearY data_transform · level 1 · ran; the contract check could not run · f5e3179cafd9393a
  15. Solarize data_transform · level 1 · ran; the contract check could not run · 70eab251c4b2bce2
  16. SolarizeAdd helper · level 0 · unverified · fcce9b35a12cd32c
  17. TranslateXabs helper · level 1 · ran; the contract check could not run · d6e5e2e212d3e912
  18. 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

  1. 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

Data AugmentationImage AugmentationImage Classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
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

1x1 ConvolutionAutoAugmentAverage PoolingBatch NormalizationBottleneck Residual BlockColorJitterConvolutionCutoutDropoutFast AutoAugmentGlobal Average PoolingKaiming InitializationLSTMMax PoolingReLUResidual BlockResidual ConnectionSigmoid ActivationTanh 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