Papers › CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features

13 May 2019ICCV 2019 10arXiv:1905.04899archive 2025-07-28

Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, Youngjoon Yoo

Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers. They have proved to be effective for guiding the model to attend on less discriminative parts of objects (e.g. leg as opposed to head of a person), thereby letting the network generalize better and have better object localization capabilities. On the other hand, current methods for regional dropout remove informative pixels on training images by overlaying a patch of either black pixels or random noise. Such removal is not desirable because it leads to information loss and inefficiency during training. We therefore propose the CutMix augmentation strategy: patches are cut and pasted among training images where the ground truth labels are also mixed proportionally to the area of the patches. By making efficient use of training pixels and retaining the regularization effect of regional dropout, CutMix consistently outperforms the state-of-the-art augmentation strategies on CIFAR and ImageNet classification tasks, as well as on the ImageNet weakly-supervised localization task. Moreover, unlike previous augmentation methods, our CutMix-trained ImageNet classifier, when used as a pretrained model, results in consistent performance gains in Pascal detection and MS-COCO image captioning benchmarks. We also show that CutMix improves the model robustness against input corruptions and its out-of-distribution detection performances. Source code and pretrained models are available at https://github.com/clovaai/CutMix-PyTorch.

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

No sample from the archive's official repository (clovaai/CutMix-PyTorch) is linked to this paper; the 23 samples below come from 14 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository. Syntology harvested code from clovaai/CutMix-PyTorch for another paper.

clovaai/CutMix-PyTorch: Syntology's graph links these samples to arXiv:2502.06434 (its page on Syntology; that paper's own run record: 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); nothing checks that they implement this paper's method.

Syntology 24 code samples: 23 from 14 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 24: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 23 samples from 14 repositories, 17 ran (10 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 6 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

clovaai/CutMix-PyTorch officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to arXiv:2502.06434 (its page on Syntology; that paper's own run record: 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); nothing checks that they implement this paper's method. report
Bennie-Han/Image-augementation-pytorch mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
DevBruce/CutMixImageDataGenerator_For_Keras mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
IlyaDobrynin/GridMixup mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Kaushal28/CutMix-Regularization-using-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
PsorTheDoctor/microarray-data mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
SyogoShibuya/Chainer-Cutmix mentioned on GitHubSyntology: not harvested report
TianshuXie/Cut-Thumbnail mentioned on GitHubpytorchSyntology: not harvested report
Westlake-AI/openmixup mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
airplane2230/keras_cutmix mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
dongdong69/MixAugmentation mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
hh-xiaohu/Image-augementation-pytorch mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
hysts/pytorch_cutmix mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ildoonet/cutmix mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
jis478/cutmix_tensorflow2 mentioned on GitHubtfSyntology: not harvested report
js-aguiar/wheat-object-detection mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified) and EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
juergenlandauer/Maya-Challenge mentioned on GitHubpytorchSyntology: not harvested report
kboseong/RotNet mentioned on GitHubpytorchSyntology: not harvested report
liuch37/image-processing mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
sangHa0411/ImageNet mentioned on GitHubpytorchSyntology: not harvested report
sangHa0411/VIT mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
toshi-k/kaggle-bengaliai-handwritten-grapheme-classification mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
xden2331/attentive_cutmix mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
jis478/Tensorflow tfSyntology: 1 sample, 0 ran · 1 unverified report
kornia/kornia pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer (arXiv:2110.02178; that paper's own run record: 53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmclassification pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reversible Vision Transformers (arXiv:2302.04869; that paper's own run record: 24 ran (of which 5 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
pytorch/vision pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
wangermeng2021/FastClassification tfSyntology: 1 sample, 1 ran (0 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: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 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
2ran · our draft was wrong
5ran; the contract check could not run
8ran
7unverified

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 14 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. 1 sample is listed last, in a group without a repository. “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.

DevBruce/CutMixImageDataGenerator_For_Keras community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
CutMixImageDataGenerator cutmix_keras.py ran MIT (permissive) · feb9e03bf1c29e48 · report fixture: returned CutMixImageDataGenerator · level recorded 2026-09-22
IlyaDobrynin/GridMixup community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GridMixupLoss gridmix/gridmix_pytorch.py ran MIT (permissive) · fe1a906546003ac6 · report fixture: returned GridMixupLoss · level recorded 2026-09-22
PsorTheDoctor/microarray-data community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
cutmix in 11 papers utils/augmentation.py ran · our draft was wrong fingerprinted no licence file found · pointer only · bdf0f6543801b45c · report fixture: signature img1:ndarray/2/int, img2:ndarray/2/int, n_patches:int/0/int, patch_width:int/0/int, patch_height:int/0/int · returned ndarray · level recorded 2026-09-22
Westlake-AI/openmixup community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
_no_repeat_shuffle_idx openmixup/models/augments/cutmix.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · ccc813c9ad477514 · report fixture: returned Tensor · level recorded 2026-09-22
cutmix in 11 papers openmixup/models/augments/cutmix.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · ed79cd2e87b6c30d · report fixture: returned tuple · level recorded 2026-09-22
airplane2230/keras_cutmix community (archive-listed) 1 sample, 0 ran · 1 unverified
CutMixGenerator cutmix_generator.py unverified no licence file found · pointer only · 793e8454c053efa6 · report
hysts/pytorch_cutmix community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
cutmix in 11 papers cutmix.py ran · our draft was wrong MIT (permissive) · de3489ea88a14549 · report fixture: signature batch:tuple/1/Tensor, alpha:float/0/float · returned tuple · level recorded 2026-09-22
ildoonet/cutmix community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
CutMix cutmix/cutmix.py ran MIT (permissive) · 88fd3e4e4d1fa77c · report fixture: returned CutMix · level recorded 2026-09-22
onehot in 39 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
cutmix/cutmix.py ran · honoured contract MIT (permissive) · a2847ea5f23c1e07 · report fixture: signature size:int/0/int, target:int/0/int · returned Tensor · level recorded 2026-09-22
rand_bbox in 63 papers cutmix/cutmix.py unverified MIT (permissive) · b3d09a4dd10e16e3 · report
liuch37/image-processing community (archive-listed) 1 sample, 0 ran · 1 unverified
cutmix in 11 papers augmentation/cutmix_pytorch.py unverified Apache-2.0 (permissive) · 8c13b211bd42a04c · report
sangHa0411/VIT community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
CutMix cutmix.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · ba67dfd90f9a6f3a · report fixture: signature a_image:Tensor/4/float, a_label:Tensor/1/float · returned tuple · level recorded 2026-09-22
toshi-k/kaggle-bengaliai-handwritten-grapheme-classification community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
BengaliCutMixDataset source/02_nn_solution/debug_dataset.py ran Apache-2.0 (permissive) · 692f9c66ea826dc6 · report fixture: returned BengaliCutMixDataset · level recorded 2026-09-22
BengaliDataset source/02_nn_solution/debug_dataset.py ran Apache-2.0 (permissive) · 5c69813c92b3303b · report fixture: returned BengaliDataset · level recorded 2026-09-22
bbox source/02_nn_solution/debug_dataset.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 7e848e7faedb674a · report fixture: signature img:ndarray/2/int · returned tuple · level recorded 2026-09-22
crop_resize in 16 papers source/02_nn_solution/debug_dataset.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 7406ca7275b897ae · report fixture: signature img0:ndarray/2/int, size:int/0/int, pad:int/0/int · returned ndarray · level recorded 2026-09-22
get_augmenter source/02_nn_solution/debug_dataset.py ran; the contract check could not run (DEP_MISSING) · metamorphic tier: deterministic Apache-2.0 (permissive) · 5d040cba7a3612d3 · report fixture: signature p:float/0/float · returned Compose · level recorded 2026-09-22
debug_cutmix source/02_nn_solution/debug_dataset.py unverified Apache-2.0 (permissive) · 04e6604fd0b16404 · report
xden2331/attentive_cutmix community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
replace_attentive_regions attentive_image.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · bc4cc5323c8e7811 · report fixture: signature rand_img:Image/0/?, image:Image/0/?, attentive_regions:list/1/tuple · returned Image · level recorded 2026-09-22
replace_attentive_region attentive_image.py unverified MIT (permissive) · 49ab4c6f3305f3c0 · report
jis478/Tensorflow community (archive-listed) 1 sample, 0 ran · 1 unverified
rand_bbox in 63 papers TF2.0/Cutmix/Functions.py unverified no licence file found · pointer only · c5224b4839efbc28 · report
pytorch/vision community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RandomCutMix references/classification/transforms.py ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · d4b0790e48bdd732 · report fixture: returned RandomCutMix · level recorded 2026-09-22
wangermeng2021/FastClassification community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Cutmix augment/cutmix.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 30fde01cef8dc1cb · report fixture: signature batch_imgs:ndarray/4/float, one_hot_batch_labels:ndarray/2/float · returned tuple · level recorded 2026-09-22
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
rand_bbox in 63 papers repository not located unverified licence of this copy not recorded · d34a085d71b8f4b5 · 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. 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.

14 assemblies on this paper: 14 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

14 sibling assemblies for CutMix (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 14 sibling assemblies; the other 2 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for CutMix (graph method: CutMix). 6 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. debug_cutmix entry · level 0 · unverified · 04e6604fd0b16404
  2. BengaliCutMixDataset data_transform · level 1 · ran · 692f9c66ea826dc6
  3. get_augmenter helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 5d040cba7a3612d3
  4. BengaliDataset helper · level 1 · ran · 5c69813c92b3303b
  5. crop_resize helper · level 1 · ran; the contract check could not run (RAISES) · 7406ca7275b897ae
  6. bbox helper · level 1 · ran · honoured contract · 7e848e7faedb674a

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

one of 14 siblings

  1. rand_bbox entry · level 0 · unverified · c5224b4839efbc28

harvested Assembly for CutMix (graph method: CutMix). 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 14 siblings

  1. RandomCutMix entry · level 1 · ran · d4b0790e48bdd732

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

one of 14 siblings

  1. CutMixGenerator entry · level 0 · unverified · 793e8454c053efa6

harvested Assembly for CutMix (graph method: CutMix). 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 14 siblings

  1. CutMixImageDataGenerator entry · level 1 · ran · feb9e03bf1c29e48

harvested Assembly for CutMix (graph method: CutMix). 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 14 siblings

  1. cutmix entry · level 1 · ran · our draft was wrong · de3489ea88a14549

harvested Assembly for CutMix (graph method: CutMix). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. cutmix entry · level 0 · unverified · 8c13b211bd42a04c
  2. rand_bbox helper · level 0 · unverified · d34a085d71b8f4b5

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

one of 14 siblings

  1. CutMix entry · level 1 · ran · 88fd3e4e4d1fa77c
  2. onehot helper · level 1 · ran · honoured contract · a2847ea5f23c1e07
  3. rand_bbox helper · level 0 · unverified · b3d09a4dd10e16e3

harvested Assembly for CutMix (graph method: CutMix). 2 bricks; 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) · 1 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. replace_attentive_regions entry · level 1 · ran; the contract check could not run (RAISES) · bc4cc5323c8e7811
  2. replace_attentive_region helper · level 0 · unverified · 49ab4c6f3305f3c0

harvested Assembly for CutMix (graph method: CutMix). 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 14 siblings

  1. GridMixupLoss entry · level 1 · ran · fe1a906546003ac6

harvested Assembly for CutMix (graph method: CutMix). 4 bricks; individually on a fixture: 3 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; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 14 siblings

  1. cutmix entry · level 1 · ran; the contract check could not run (RAISES) · ed79cd2e87b6c30d
  2. _no_repeat_shuffle_idx helper · level 1 · ran; the contract check could not run (RAISES) · ccc813c9ad477514
  3. batch_shuffle_ddp helper · level 0 · unverified · d6b836d9b156da28
  4. concat_all_gather helper · level 1 · ran; the contract check could not run · fa052d95a1f73aa9

harvested Assembly for CutMix (graph method: CutMix). 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 14 siblings

  1. Cutmix entry · level 1 · ran · 30fde01cef8dc1cb
  1. cutmix · d9b8d3ef109da7de · 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 · assemblies[12] in the JSON twin
  2. CutMix · fe29d99c3a2374ee · 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 · assemblies[13] in the JSON twin

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="1905.04899") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Domain GeneralizationImage CaptioningImage ClassificationObject LocalizationOut-of-Distribution DetectionOut-of-Distribution GeneralizationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A CutMix (ResNet-50) Top-1 accuracy % 7.3 #34 of 39 Archive leaderboard report
Image Captioning COCO (Common Objects in Context) NIC (ResNet-50, CutMix) BLEU-1 64.2 #12 of 17 Archive leaderboard report
Image Captioning COCO (Common Objects in Context) NIC (ResNet-50, CutMix) BLEU-2 46.3 #12 of 17 Archive leaderboard report
Image Captioning COCO (Common Objects in Context) NIC (ResNet-50, CutMix) BLEU-3 33.6 #12 of 17 Archive leaderboard report
Image Captioning COCO (Common Objects in Context) NIC (ResNet-50, CutMix) BLEU-4 24.9 #12 of 17 Archive leaderboard report
Image Captioning COCO (Common Objects in Context) NIC (ResNet-50, CutMix) CIDEr 77.6 #12 of 17 Archive leaderboard report
Image Captioning COCO (Common Objects in Context) NIC (ResNet-50, CutMix) METEOR 23.1 #12 of 17 Archive leaderboard report
Image Captioning COCO (Common Objects in Context) NIC (ResNet-50, CutMix) ROUGE 49 #12 of 17 Archive leaderboard report
Image Classification CIFAR-10 PyramidNet-200 + CutMix Percentage correct 97.12 #92 of 265 Archive leaderboard report
Image Classification CIFAR-100 PyramidNet-200 + Shakedrop + Cutmix Percentage correct 86.19 #55 of 211 Archive leaderboard report
Image Classification ImageNet ResNeXt-101 (CutMix) Top 1 Accuracy 80.53% #694 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-50 (CutMix) Top 1 Accuracy 78.4% #835 of 1060 Archive leaderboard report
Image Classification OmniBenchmark CutMix Average Top-1 Accuracy 31.1 #19 of 22 Archive leaderboard report
Semantic Segmentation ACDC Scribbles CutMix Dice (Average) 70.5% #4 of 6 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: CutMix

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionCutMixDropoutGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionSGD with MomentumStep Decay

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