Papers › AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic...

AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation

10 Mar 2021CVPR 2021 1arXiv:2103.05863archive 2025-07-28

Denis Gudovskiy, Luca Rigazio, Shun Ishizaka, Kazuki Kozuka, Sotaro Tsukizawa

AutoAugment has sparked an interest in automated augmentation methods for deep learning models. These methods estimate image transformation policies for train data that improve generalization to test data. While recent papers evolved in the direction of decreasing policy search complexity, we show that those methods are not robust when applied to biased and noisy data. To overcome these limitations, we reformulate AutoAugment as a generalized automated dataset optimization (AutoDO) task that minimizes the distribution shift between test data and distorted train dataset. In our AutoDO model, we explicitly estimate a set of per-point hyperparameters to flexibly change distribution of train data. In particular, we include hyperparameters for augmentation, loss weights, and soft-labels that are jointly estimated using implicit differentiation. We develop a theoretical probabilistic interpretation of this framework using Fisher information and show that its complexity scales linearly with the dataset size. Our experiments on SVHN, CIFAR-10/100, and ImageNet classification show up to 9.3% improvement for biased datasets with label noise compared to prior methods and, importantly, up to 36.6% gain for underrepresented SVHN classes.

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 7 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 6 ran (4 with no instrument failure; 2 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.

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.

gudovskiy/autodo officialmentioned in papermentioned on GitHubpytorchSyntology: 7 samples, 6 ran (2 instrument-failed) · 1 unverified 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.

Code Syntology ran Syntology

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 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 · our draft was wrong
1ran; the contract check could not run
4ran
1unverified

Licence: 7 of the 7 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 gudovskiy/autodo. “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.

gudovskiy/autodo official repository 7 samples, 6 ran (2 instrument-failed) · 1 unverified
apply_augment custom_transforms/dada_augment.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 2ee8bbf5cc664aa8 · report fixture: signature img:Image/0/?, name:str/0/str, level:float/0/float · returned Image · level recorded 2026-09-24
dada_reduced_cifar10 custom_transforms/dada_augment.py ran no licence file found · pointer only · e8d4871b0093493a · report fixture: returned list · level recorded 2026-09-25
dada_reduced_cifar100 custom_transforms/dada_augment.py ran no licence file found · pointer only · 2503981c085add0b · report fixture: returned list · level recorded 2026-09-24
dada_reduced_svhn custom_transforms/dada_augment.py ran no licence file found · pointer only · fa81fe1d347ec7e7 · report fixture: returned list · level recorded 2026-09-24
dada_resnet50_rimagenet custom_transforms/dada_augment.py ran no licence file found · pointer only · e23610775abae63b · report fixture: returned list · level recorded 2026-09-24
get_augment custom_transforms/dada_augment.py ran · our draft was wrong no licence file found · pointer only · 0e01d35d9ddb931b · report fixture: signature name:str/0/str · returned tuple · level recorded 2026-09-22
DadaAugment custom_transforms/dada_augment.py unverified no licence file found · pointer only · 1e0e3c15411377ed · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AutoDO (graph method: AutoDO). 27 bricks; individually on a fixture: 26 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 22 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. DadaAugment entry · level 0 · unverified · 1e0e3c15411377ed
  2. apply_augment helper · level 1 · ran; the contract check could not run (RAISES) · 2ee8bbf5cc664aa8
  3. dada_reduced_cifar10 helper · level 1 · ran · e8d4871b0093493a
  4. dada_reduced_cifar100 helper · level 1 · ran · 2503981c085add0b
  5. dada_reduced_svhn helper · level 1 · ran · fa81fe1d347ec7e7
  6. dada_resnet50_rimagenet helper · level 1 · ran · e23610775abae63b
  7. get_augment helper · level 1 · ran · our draft was wrong · 0e01d35d9ddb931b
  8. AutoContrast data_transform · level 1 · ran · our draft was wrong · 4a0ac9d611e018bc
  9. Brightness data_transform · level 1 · ran; the contract check could not run · 993134d3c95bcf92
  10. Color data_transform · level 1 · ran; the contract check could not run · ccaa14b841bf44dc
  11. Contrast data_transform · level 1 · ran; the contract check could not run · 35f5a6d3913e6b0e
  12. Cutout data_transform · level 1 · ran; the contract check could not run · f90119cfdd38ef56
  13. CutoutAbs helper · level 1 · ran; the contract check could not run · 03ecbd868107e6f7
  14. Equalize data_transform · level 1 · ran · our draft was wrong · 4befb1744e90f3a1
  15. Invert data_transform · level 1 · ran · our draft was wrong · f5f0bf976dfcf068
  16. Posterize data_transform · level 1 · ran; the contract check could not run · d2a9bd74240b6944
  17. Posterize2 helper · level 1 · ran; the contract check could not run · 067680c1cc9f4b97
  18. Rotate data_transform · level 1 · ran · our draft was wrong · 21c6427b09f14649
  19. Sharpness data_transform · level 1 · ran; the contract check could not run · e1ccc58bf76a30b9
  20. ShearX data_transform · level 1 · ran; the contract check could not run · b92936d1f2ac3e6c
  21. ShearY data_transform · level 1 · ran; the contract check could not run · 008c64b77c4ae4c9
  22. Solarize data_transform · level 1 · ran; the contract check could not run · 70eab251c4b2bce2
  23. TranslateX data_transform · level 1 · ran; the contract check could not run · ab50d5bbcf589623
  24. TranslateXAbs helper · level 1 · ran; the contract check could not run · b1fc55be13be06e7
  25. TranslateY data_transform · level 1 · ran; the contract check could not run · d4b73cc9fa9b08ae
  26. TranslateYAbs helper · level 1 · ran; the contract check could not run · 15ceb820d17f0a5c
  27. augment_list helper · level 1 · ran · our draft was wrong · b1cd4e4b4bba7f8c

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="2103.05863") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AutoAugmentLSTMSigmoid ActivationTanh Activation

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