Papers › Improved Regularization of Convolutional Neural Networks with Cutout

Improved Regularization of Convolutional Neural Networks with Cutout

15 Aug 2017arXiv:1708.04552archive 2025-07-28

Terrance DeVries, Graham W. Taylor

Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks. However, due to the model capacity required to capture such representations, they are often susceptible to overfitting and therefore require proper regularization in order to generalize well. In this paper, we show that the simple regularization technique of randomly masking out square regions of input during training, which we call cutout, can be used to improve the robustness and overall performance of convolutional neural networks. Not only is this method extremely easy to implement, but we also demonstrate that it can be used in conjunction with existing forms of data augmentation and other regularizers to further improve model performance. We evaluate this method by applying it to current state-of-the-art architectures on the CIFAR-10, CIFAR-100, and SVHN datasets, yielding new state-of-the-art results of 2.56%, 15.20%, and 1.30% test error respectively. Code is available at https://github.com/uoguelph-mlrg/Cutout

PaperPDFCodeCode 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

The archive's official repository (uoguelph-mlrg/Cutout) was not harvested; the 24 samples below come from 10 community repositories.

Syntology 24 code samples harvested from 10 repositories linked to this paper: 21 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 8 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 24 samples from 10 repositories, 21 ran (9 with no instrument failure; 12 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 7 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.

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

uoguelph-mlrg/Cutout officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
KentaItakura/CNN-classification-using-random-erasing-and-cut-out mentioned on GitHubSyntology: not harvested report
LMaxence/Cifar10_Classification mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
PsorTheDoctor/microarray-data mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Ximilar-com/tf-image mentioned on GitHubtfSyntology: 5 samples, 4 ran (2 instrument-failed) · 1 unverified report
YaCpotato/B4ResearchDeepaugment mentioned on GitHubSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
YaCpotato/deepaugmentFix mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AutoAugment: Learning Augmentation Policies from Data (arXiv:1805.09501; that paper's own run record: 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); nothing checks that they implement this paper's method. report
abcp4/DAPytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AutoAugment: Learning Augmentation Policies from Data (arXiv:1805.09501; that paper's own run record: 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); nothing checks that they implement this paper's method. report
barisozmen/deepaugment mentioned on GitHubSyntology: 5 samples, 5 ran (2 instrument-failed) · 0 unverified report
changewOw/Cutout-numpy mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
dishen12/Cuout_modify mentioned on GitHubpytorchSyntology: not harvested report
eaguaida/TF_EnsNet- mentioned on GitHubtfSyntology: not harvested report
etetteh/sota-data-augmentation-and-optimizers mentioned on GitHubpytorchSyntology: 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) and AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty (arXiv:1912.02781; that paper's own run record: 46 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 2 violated, 3 with no contract checked; 37 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
felixgwu/img_classification_pk_pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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) and 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); nothing checks that they implement this paper's method. report
khanrc/pt.fractalnet mentioned on GitHubpytorchSyntology: not harvested report
kschwethelm/hyperboliccv mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fully Hyperbolic Convolutional Neural Networks for Computer Vision (arXiv:2303.15919; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
lewis-morris/image_augment mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lnstadrum/fastaugment mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
lyxxn0414/test-data-generation mentioned on GitHubtfSyntology: 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
mingsun-tse/good-da-in-kd mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
namakemono/kaggle-alaska2-image-steganalysis mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
oxygen0605/ImageClassification mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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); nothing checks that they implement this paper's method. report
psr007ps/NeuralNetAugmentations mentioned on GitHubSyntology: not harvested report
senthilva/CNN_CIFAR10_gradcam_cutout mentioned on GitHubSyntology: not harvested report
sour4bh/cifar-10 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ymittal23/PlayWithCifar mentioned on GitHubtfSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
albumentations-team/albumentations pytorchSyntology: 5 samples, 5 ran (5 instrument-failed) · 0 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.

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

24 samples harvested: 21 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 12 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 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.

3ran · honoured contract
3ran · violated contract
4ran · our draft was wrong
8ran; the contract check could not run
3ran
3unverified

Licence: 5 of the 24 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 10 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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

PsorTheDoctor/microarray-data community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
cutout in 17 papers utils/augmentation.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 4a5f5e6272b139bf · report fixture: signature img:ndarray/2/float, n_patches:int/0/int, patch_width:int/0/int, patch_height:int/0/int · returned ndarray · level recorded 2026-09-22
Ximilar-com/tf-image community (archive-listed) 5 samples, 4 ran (2 instrument-failed) · 1 unverified
_bboxes_to_absolute tf_image/core/erase.py ran · honoured contract fingerprinted MIT (permissive) · c19f6a181aae4d15 · report fixture: signature image:EagerTensor/3/float, bboxes:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
_bboxes_to_relative tf_image/core/erase.py ran · violated contract fingerprinted MIT (permissive) · 909fa545052a99f8 · report fixture: signature image:EagerTensor/3/float, bboxes:EagerTensor/2/float · returned SymbolicTensor · level recorded 2026-09-22
_random_erasing tf_image/core/erase.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 8a71fb8f5184a010 · report fixture: signature image:EagerTensor/4/float, max_area:int/0/int, erased_value:float/0/float · returned EagerTensor · level recorded 2026-09-22
convert_type in 5 papers tf_image/core/erase.py ran · our draft was wrong MIT (permissive) · c632411042c122ec · report fixture: signature function:callable/0/? · returned function · level recorded 2026-09-22
random_erasing tf_image/core/erase.py unverified MIT (permissive) · 53b07796c4e8aaae · report
YaCpotato/B4ResearchDeepaugment community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
create_cutout_mask deepaugment/lib/cutout.py ran · our draft was wrong MIT (permissive) · 9b004be093898ee9 · report fixture: signature img_height:int/0/int, img_width:int/0/int, num_channels:int/0/int, size:int/0/int · returned tuple · level recorded 2026-09-22
cutout_numpy deepaugment/lib/cutout.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · b09aaca166fba057 · report fixture: signature img:ndarray/3/float, size:int/0/int · returned ndarray · level recorded 2026-09-22
barisozmen/deepaugment community (archive-listed) 5 samples, 5 ran (2 instrument-failed) · 0 unverified
apply_policy in 9 papers src/deepaugment/transforms.py ran; the contract check could not run (RAISES) MIT (permissive) · 725a089326cde6b7 · report fixture: signature image:ndarray/3/int, policy:list/1/tuple · returned ndarray · level recorded 2026-09-22
clamp in 78 papers
census: 7 implementations from 8 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 3 of 4, arg 1: rank 2, kind float, dtype float64
src/deepaugment/transforms.py ran · violated contract fingerprinted MIT (permissive) · 77de6eeb25f3b2cc · report fixture: signature x:ndarray/2/float, min_val:float/0/float, max_val:float/0/float · returned ndarray · level recorded 2026-09-22
make_transform in 17 papers src/deepaugment/transforms.py ran · our draft was wrong MIT (permissive) · a88a0ebd4d7051a8 · report fixture: signature name:str/0/str, magnitude:float/0/float · returned RandomRotation · level recorded 2026-09-22
numpy_to_pil in 37 papers src/deepaugment/transforms.py ran · honoured contract MIT (permissive) · 138b15df97d8f22d · report fixture: signature image:ndarray/2/int · returned Image · level recorded 2026-09-22
pil_to_numpy src/deepaugment/transforms.py ran · violated contract MIT (permissive) · 88618f34ed54e2bc · report fixture: signature image:Image/0/? · returned ndarray · level recorded 2026-09-22
changewOw/Cutout-numpy community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Cutout in 6 papers cutout.py ran no licence file found · pointer only · e4f60cb273f96e43 · report fixture: returned Cutout · level recorded 2026-09-22
lewis-morris/image_augment community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Augmentation ImageAugment/basic_augmentation.py ran GPL-3.0 (copyleft) · pointer only · 65b19ebc3c066d46 · report fixture: returned Augmentation · level recorded 2026-09-22
lnstadrum/fastaugment community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
listify in 14 papers tensorflow/fast_augment.py ran · honoured contract fingerprinted MIT (permissive) · f66d6a0103a637b1 · report fixture: signature it:int/0/int · returned list · level recorded 2026-09-22
augment in 36 papers tensorflow/fast_augment.py unverified MIT (permissive) · 57014965cf3804dc · report
mingsun-tse/good-da-in-kd community (archive-listed) 1 sample, 0 ran · 1 unverified
cutout in 17 papers helper/loops.py unverified no licence file found · pointer only · 0972fd225cc9b653 · report
sour4bh/cifar-10 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Cutout in 6 papers cutout.py ran fingerprinted no licence file found · pointer only · 9712ea58142deac2 · report fixture: returned Cutout · level recorded 2026-09-22
albumentations-team/albumentations community (archive-listed) 5 samples, 5 ran (5 instrument-failed) · 0 unverified
apply_inpainting albumentations/augmentations/dropout/functional.py ran; the contract check could not run (DEP_MISSING) MIT (permissive) · 6ffc19e585a6e93e · report fixture: signature img:ndarray/3/int, holes:ndarray/2/int, method:str/0/str · returned ndarray · level recorded 2026-09-22
cutout in 17 papers albumentations/augmentations/dropout/functional.py ran; the contract check could not run (DEP_MISSING) MIT (permissive) · d912ce51776a4d78 · report fixture: signature img:ndarray/3/int, holes:ndarray/2/int, fill:tuple/1/int, random_generator:Generator/0/? · returned ndarray · level recorded 2026-09-22
fill_holes_with_random albumentations/augmentations/dropout/functional.py ran; the contract check could not run (DEP_MISSING) MIT (permissive) · 8e25588616aec646 · report fixture: signature img:ndarray/3/int, holes:ndarray/2/int, random_generator:Generator/0/?, uniform:bool/0/bool · returned ndarray · level recorded 2026-09-24
fill_holes_with_value albumentations/augmentations/dropout/functional.py ran; the contract check could not run (RAISES) MIT (permissive) · 108e7feedea6f696 · report fixture: signature img:ndarray/3/int, holes:ndarray/2/int, fill:ndarray/1/int · returned ndarray · level recorded 2026-09-22
generate_random_fill albumentations/augmentations/dropout/functional.py ran; the contract check could not run (DEP_MISSING) MIT (permissive) · 2e63069222acc030 · report fixture: signature dtype:UInt8DType/0/?, shape:tuple/1/int, random_generator:Generator/0/? · 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.

10 assemblies on this paper: 10 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Cutout (graph method: Cutout). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. Cutout entry · level 1 · ran · 9712ea58142deac2

harvested Assembly for Cutout (graph method: Cutout). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. Cutout entry · level 1 · ran · e4f60cb273f96e43

harvested Assembly for Cutout (graph method: Cutout). 5 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. random_erasing entry · level 0 · unverified · 53b07796c4e8aaae
  2. _random_erasing helper · level 1 · ran; the contract check could not run (RAISES) · 8a71fb8f5184a010
  3. convert_type helper · level 1 · ran · our draft was wrong · c632411042c122ec
  4. _bboxes_to_absolute helper · level 1 · ran · honoured contract · c19f6a181aae4d15
  5. _bboxes_to_relative helper · level 1 · ran · violated contract · 909fa545052a99f8

harvested Assembly for Cutout (graph method: Cutout). 2 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. cutout_numpy entry · level 1 · ran; the contract check could not run (RAISES) · b09aaca166fba057
  2. create_cutout_mask helper · level 1 · ran · our draft was wrong · 9b004be093898ee9

harvested Assembly for Cutout (graph method: Cutout). 5 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. apply_policy entry · level 1 · ran; the contract check could not run (RAISES) · 725a089326cde6b7
  2. make_transform data_transform · level 1 · ran · our draft was wrong · a88a0ebd4d7051a8
  3. numpy_to_pil helper · level 1 · ran · honoured contract · 138b15df97d8f22d
  4. pil_to_numpy helper · level 1 · ran · violated contract · 88618f34ed54e2bc
  5. clamp helper · level 1 · ran · violated contract · 77de6eeb25f3b2cc

harvested Assembly for Cutout (graph method: Cutout). 1 brick; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. cutout entry · level 1 · ran · our draft was wrong · 4a5f5e6272b139bf

harvested Assembly for Cutout (graph method: Cutout). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 10 siblings

  1. Augmentation entry · level 1 · ran · 65b19ebc3c066d46

harvested Assembly for Cutout (graph method: Cutout). 5 bricks; individually on a fixture: 5 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; 5 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. cutout entry · level 1 · ran; the contract check could not run (DEP_MISSING) · d912ce51776a4d78
  2. apply_inpainting helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 6ffc19e585a6e93e
  3. fill_holes_with_random helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 8e25588616aec646
  4. fill_holes_with_value helper · level 1 · ran; the contract check could not run (RAISES) · 108e7feedea6f696
  5. generate_random_fill helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 2e63069222acc030

harvested Assembly for Cutout (graph method: Cutout). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 10 siblings

  1. cutout entry · level 0 · unverified · 0972fd225cc9b653

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

one of 10 siblings

  1. augment entry · level 0 · unverified · 57014965cf3804dc
  2. listify helper · level 1 · ran · honoured contract · f66d6a0103a637b1

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="1708.04552") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationDomain GeneralizationImage AugmentationImage ClassificationOut-of-Distribution GeneralizationSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A Cutout (ResNet-50) Top-1 accuracy % 4.4 #36 of 39 Archive leaderboard report
Image Classification STL-10 Cutout Percentage correct 87.26 #46 of 117 Archive leaderboard report
Image Classification SVHN Cutout Percentage error 1.30 #6 of 62 Archive leaderboard report
Semi-Supervised Image Classification STL-10 CutOut Accuracy 87.26 #3 of 3 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: Cutout

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionCutoutGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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