Papers › mixup: Beyond Empirical Risk Minimization

mixup: Beyond Empirical Risk Minimization

25 Oct 2017ICLR 2018 1arXiv:1710.09412archive 2025-07-28

Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple linear behavior in-between training examples. Our experiments on the ImageNet-2012, CIFAR-10, CIFAR-100, Google commands and UCI datasets show that mixup improves the generalization of state-of-the-art neural network architectures. We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.

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

The archive's official repository (facebookresearch/mixup-cifar10) was not harvested; the 47 samples below come from 28 community repositories.

Syntology 47 code samples harvested from 28 repositories linked to this paper: 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. Where Syntology's instrument failed: 8 where our contract draft was wrong; 14 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 47 samples from 28 repositories, 36 ran (14 with no instrument failure; 22 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 13 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

facebookresearch/mixup-cifar10 officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
5m0k3/gwd-efficientdet-pytorch mentioned on GitHubpytorchSyntology: not harvested report
5m0k3/gwd-yolov5-pytorch mentioned on GitHubpytorchSyntology: not harvested report
AngusG/bn-advex-zhang-fixup 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); 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
Brunogomes97/Imdb mentioned on GitHubSyntology: not harvested report
CaoShuning/MIXUP mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Hazelsuko07/InstaHide mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
JunweiLiang/Object_Detection_Tracking mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Real-Time Multi-Object Tracking (arXiv:1909.12605; that paper's own run record: 30 ran (of which 0 constructed an object rather than computing a result; 28 with no instrument failure: 0 honoured, 0 violated, 28 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
LeiLiu-byte/the-Essence-of-LT-Rocognition mentioned on GitHubpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
P2333/Mixup-Inference mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks (arXiv:1909.11515; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
PsorTheDoctor/microarray-data mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
RohitDhankar/kaggle_wheat mentioned on GitHubpytorchSyntology: not harvested report
Ryoo72/dimension-wise_mixup mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
SarthakYadav/audax mentioned on GitHubjaxSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
Shubhammawa/MixMatch-Semi-Supervised-Learning mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Taoudi/DataAugmentation mentioned on GitHubtfMITSyntology: not harvested report
Taoudi/ImbalancedData mentioned on GitHubtfMITSyntology: not harvested report
Westlake-AI/openmixup mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
Yangget/Mixup_All-use mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
acmiyaguchi/birdclef-2022 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
akjgskwi/mixup_chainer mentioned on GitHubMITSyntology: not harvested report
amerch/CIFAR100-Training mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Explaining and Harnessing Adversarial Examples (arXiv:1412.6572; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
andychinka/dcase-challenge mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
ben-davidson-6/fixup 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); nothing checks that they implement this paper's method. report
dongdong69/MixAugmentation mentioned on GitHubSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
erichson/noisy_mixup mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
facebookresearch/ClassyVision mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (5 instrument-failed) · 1 unverified report
google-research/diffstride mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning strides in convolutional neural networks (arXiv:2202.01653; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 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
hongyi-zhang/Fixup mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability (arXiv:2103.00065; that paper's own run record: 0 ran · 2 unverified); nothing checks that they implement this paper's method. report
hongyi-zhang/mixup mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
iver56/audiomentations mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AudioCLIP: Extending CLIP to Image, Text and Audio (arXiv:2106.13043; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jianshen92/stanford-car-grab-challenge mentioned on GitHubpytorchSyntology: not harvested report
jmaronas/calibration_MixupDNN_ARCLoss.pytorch mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
jonnor/datascience-master mentioned on GitHubSyntology: not harvested report
js-aguiar/wheat-object-detection mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lRomul/argus-freesound mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
leehomyc/mixup_pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
lnstadrum/fastaugment mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Regularization of Convolutional Neural Networks with Cutout (arXiv:1708.04552; that paper's own run record: 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); nothing checks that they implement this paper's method. report
makeyourownmaker/mixup mentioned on GitHubpytorchGPL-2.0Syntology: not harvested report
mingsun-tse/good-da-in-kd mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
nikolaev-n/CocktailPartySpeakerRecognition mentioned on GitHubApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
psr007ps/NeuralNetAugmentations mentioned on GitHubSyntology: not harvested report
rit-git/Snippext_public mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MixMatch: A Holistic Approach to Semi-Supervised Learning (arXiv:1905.02249; that paper's own run record: 47 ran (of which 8 constructed an object rather than computing a result; 27 with no instrument failure: 8 honoured, 0 violated, 19 with no contract checked; 20 where Syntology's instrument failed) · 16 unverified); nothing checks that they implement this paper's method. 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
sailist/thexp-implement mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
sayakpaul/FunMatch-Distillation mentioned on GitHubtfSyntology: not harvested report
scut-aitcm/Competitive-Inner-Imaging-SENet mentioned on GitHubtfSyntology: not harvested report
scut-aitcm/CompetitiveSENet mentioned on GitHubtfSyntology: not harvested report
simongrest/farm-pin-crop-detection-challenge mentioned on GitHubApache-2.0Syntology: not harvested report
simongrest/kaggle-freesound-audio-tagging-2019 mentioned on GitHubSyntology: not harvested report
smilelab-fl/fednoisy mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
stanl1y/med_TwoCycleLearning-and-MixUp mentioned on GitHubSyntology: not harvested report
tanmaypandey7/wheat-detection mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (2 instrument-failed) · 1 unverified report
teang1995/satellite_image_task mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
toshi-k/kaggle-bengaliai-handwritten-grapheme-classification mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
transcendentsky/mixup mentioned on GitHubpytorchBSD-3-ClauseSyntology: not harvested report
tugstugi/pytorch-speech-commands mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
tusharip/augmentations mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
yell/kaggle-camera mentioned on GitHubpytorchMITSyntology: not harvested report
yuleiqin/capro mentioned on GitHubpytorchSyntology: not harvested report
yuleiqin/fopro mentioned on GitHubpytorchSyntology: not harvested report
ENSTA-U2IS-AI/torch-uncertainty pytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
OFRIN/Tensorflow_MixUp tfSyntology: 1 sample, 0 ran · 1 unverified report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
jankrepl/mildlyoverfitted jaxSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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
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

47 samples harvested: 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. “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.

8ran · our draft was wrong
14ran; the contract check could not run
14ran
11unverified

Licence: 15 of the 47 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 28 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.

Hazelsuko07/InstaHide community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
vec_mul_ten train_cross.py ran · our draft was wrong MIT (permissive) · ac26d9206e0ac500 · report fixture: signature vec:Tensor/1/float, tensor:Tensor/3/float · returned Tensor · level recorded 2026-09-24
mixup_data in 51 papers train_cross.py unverified MIT (permissive) · e7229d6a2824b389 · report
PsorTheDoctor/microarray-data community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup in 28 papers utils/augmentation.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 835392836f697b21 · report fixture: signature img1:ndarray/4/float, label1:ndarray/2/float, img2:ndarray/4/float, label2:ndarray/2/float, alpha:float/0/float · returned tuple · level recorded 2026-09-22
Ryoo72/dimension-wise_mixup community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup_data in 51 papers models/utils.py ran; the contract check could not run (RAISES) licence not identified · pointer only · b062bea460457feb · report fixture: returned tuple · level recorded 2026-09-22
SarthakYadav/audax community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
do_mixup in 11 papers audax/transforms/mixup.py ran · our draft was wrong BSD-2-Clause (permissive) · 1c7aeb910bc9f545 · report fixture: signature key:ArrayImpl/1/int, inputs:ArrayImpl/4/float, targets:ArrayImpl/2/float, alpha:float/0/float, mode:TrainingMode/0/? · returned tuple · level recorded 2026-09-22
TrainingMode audax/transforms/mixup.py unverified BSD-2-Clause (permissive) · 51f54dbb7240a484 · report
Shubhammawa/MixMatch-Semi-Supervised-Learning community (archive-listed) 1 sample, 0 ran · 1 unverified
mixup in 28 papers MixMatch_utils/MixMatch_utils.py unverified MIT (permissive) · 9632c4d4a17cb9c6 · report
Westlake-AI/openmixup community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
concat_all_gather in 141 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
openmixup/models/augments/mixup.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · fa052d95a1f73aa9 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22
mixup in 28 papers openmixup/models/augments/mixup.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 656d88b7d9a9e392 · report fixture: returned tuple · level recorded 2026-09-22
batch_shuffle_ddp in 6 papers openmixup/models/augments/mixup.py unverified Apache-2.0 (permissive) · d6b836d9b156da28 · report
Yangget/Mixup_All-use community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup in 28 papers Mixup.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · bc9feed0a6523697 · report fixture: signature alpha:float/0/float, batch_x:ndarray/4/float, batch_y:ndarray/2/float · returned tuple · level recorded 2026-09-22
acmiyaguchi/birdclef-2022 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Mixup birdclef/models/classifier_nn/datasets.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1b55e6c4576721e0 · report fixture: signature sample:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
andychinka/dcase-challenge community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup_data in 51 papers asc/data_aug.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 4ef20d27ae01e4c3 · report fixture: signature x:Tensor/2/float, y:Tensor/1/int, alpha:float/0/float, use_cuda:bool/0/bool, concat_ori:bool/0/bool · returned tuple · level recorded 2026-09-22
dongdong69/MixAugmentation community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MixAug MixAug.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 5fe78642cd386d74 · report fixture: signature images:list/1/ndarray, labels:list/1/ndarray · returned tuple · level recorded 2026-09-22
erichson/noisy_mixup community (archive-listed) 2 samples, 0 ran · 2 unverified
_noise src/noisy_mixup.py unverified GPL-3.0 (copyleft) · pointer only · 48b6ae3361582213 · report
do_noisy_mixup src/noisy_mixup.py unverified GPL-3.0 (copyleft) · pointer only · e4a853c8450e16b2 · report
facebookresearch/ClassyVision community (archive-listed) 6 samples, 5 ran (5 instrument-failed) · 1 unverified
_recursive_mixup classy_vision/dataset/transforms/mixup.py ran · our draft was wrong MIT (permissive) · 6d58d3dc58c56a08 · report fixture: signature sample:list/1/dict, coeff:float/0/float · returned list · level recorded 2026-09-22
cutmix_bbox_and_lam classy_vision/dataset/transforms/mixup.py ran; the contract check could not run (RAISES) MIT (permissive) · 7769dc4e190b54d4 · report fixture: signature img_shape:tuple/1/int, lam:float/0/float, ratio_minmax:NoneType/0/?, correct_lam:bool/0/bool, count:int/0/int · returned tuple · level recorded 2026-09-22
mixup_target in 22 papers classy_vision/dataset/transforms/mixup.py ran · our draft was wrong fingerprinted MIT (permissive) · 448ddfbc145b985e · report fixture: signature target:Tensor/1/int, num_classes:int/0/int, lam:float/0/float, smoothing:float/0/float · returned Tensor · level recorded 2026-09-22
rand_bbox in 63 papers classy_vision/dataset/transforms/mixup.py ran · our draft was wrong MIT (permissive) · 19ead423fd887adc · report fixture: signature img_shape:tuple/1/int, lam:float/0/float, margin:float/0/float, count:int/0/int · returned tuple · level recorded 2026-09-22
rand_bbox_minmax classy_vision/dataset/transforms/mixup.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d82c3a657cbaed6b · report fixture: signature img_shape:tuple/1/int, minmax:tuple/1/float, count:int/0/int · returned list · level recorded 2026-09-22
MixupTransform classy_vision/dataset/transforms/mixup.py unverified MIT (permissive) · 701284a14a921294 · report
hongyi-zhang/mixup community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup_data in 51 papers cifar/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic BSD-3-Clause (permissive) · c8f7fd47a7acbaa3 · report fixture: signature x:Tensor/2/float, y:Tensor/1/int, alpha:float/0/float, use_cuda:bool/0/bool · returned tuple · level recorded 2026-09-22
js-aguiar/wheat-object-detection community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DatasetRetriever source/dataset.py ran no licence file found · pointer only · 7c45621d4018ce63 · report fixture: returned DatasetRetriever · level recorded 2026-09-22
lRomul/argus-freesound community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
AddMixer src/mixers.py ran MIT (permissive) · 60fc83929db77047 · report fixture: returned AddMixer · level recorded 2026-09-22
get_random_sample src/mixers.py ran · our draft was wrong MIT (permissive) · ff05773d89bd720b · report fixture: signature dataset:MockDataset/0/? · returned tuple · level recorded 2026-09-22
leehomyc/mixup_pytorch community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
PreActResNet18 in 38 papers models/preact_resnet.py ran MIT (permissive) · b6e5f24824f19914 · report fixture: signature num_classes:int/0/int · returned PreActResNet · level recorded 2026-09-25
shuffle_minibatch main_cifar10.py ran MIT (permissive) · d3e01aa48a90e109 · report fixture: signature inputs:Tensor/4/float, targets:Tensor/1/int, mixup:bool/0/bool · returned tuple · level recorded 2026-09-26
shuffle_minibatch main_cifar100.py unverified MIT (permissive) · a3594707e07f7e69 · report
mingsun-tse/good-da-in-kd community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup in 28 papers helper/loops.py ran; the contract check could not run (RAISES) no licence file found · pointer only · f0f17df9d7c15828 · report fixture: returned tuple · level recorded 2026-09-22
nikolaev-n/CocktailPartySpeakerRecognition community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
count_files_in_dataset_dir audio_normalizer.py ran fingerprinted Apache-2.0 (permissive) · 8aadd870961992c4 · report fixture: signature dataset_dir:str/0/str, file_format:str/0/str · returned int · level recorded 2026-09-26
load_wave gen_audio_features.py ran Apache-2.0 (permissive) · 28154e77998b2963 · report fixture: signature path_to_file:str/0/str · returned tuple · level recorded 2026-09-26
parse_label_voxceleb gen_audio_features.py ran Apache-2.0 (permissive) · 268ef97cebd35bef · report fixture: signature path_to_file:str/0/str · returned int · level recorded 2026-09-26
smilelab-fl/fednoisy community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup_data in 51 papers fednoisy/utils/mixup.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 1905009bf59716f6 · report fixture: signature x:Tensor/2/float, y:Tensor/1/int, alpha:float/0/float, device:NoneType/0/? · returned tuple · level recorded 2026-09-22
tanmaypandey7/wheat-detection community (archive-listed) 3 samples, 2 ran (2 instrument-failed) · 1 unverified
load_image_and_boxes utils/utils/datasets.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 0d7e0c55bc9b54f4 · report fixture: signature self:MockDataset/0/?, index:int/0/int · returned tuple · level recorded 2026-09-22
load_mixup_images_and_boxes utils/utils/datasets.py ran · our draft was wrong GPL-3.0 (copyleft) · pointer only · 6d4ae2306a6dd42c · report fixture: signature self:MockDataset/0/?, index:int/0/int · returned tuple · level recorded 2026-09-22
load_image in 273 papers utils/utils/datasets.py unverified GPL-3.0 (copyleft) · pointer only · 96c97809b6f786f8 · report
toshi-k/kaggle-bengaliai-handwritten-grapheme-classification community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
BengaliMixUpDataset source/02_nn_solution/debug_dataset.py ran Apache-2.0 (permissive) · eda27e400dd33e72 · report fixture: returned BengaliMixUpDataset · level recorded 2026-09-22
debug_mixup source/02_nn_solution/debug_dataset.py unverified Apache-2.0 (permissive) · 9479dbe678007bc9 · report
tugstugi/pytorch-speech-commands community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
mixup in 28 papers mixup.py ran; the contract check could not run (RAISES) no licence file found · pointer only · e85b9399854d6440 · report fixture: signature inputs:Tensor/4/float, targets:Tensor/1/int, num_classes:int/0/int, alpha:int/0/int · returned tuple · 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 this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
mixup.py ran; the contract check could not run (RAISES) no licence file found · pointer only · bc878657aee7b3c0 · report fixture: signature targets:Tensor/1/int, num_classes:int/0/int · returned Tensor · level recorded 2026-09-22
tusharip/augmentations community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
mixup in 28 papers codes/vision.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 933e954914270161 · report fixture: signature images:Tensor/4/float, labels:Tensor/2/float, alpha:float/0/float · returned tuple · level recorded 2026-09-22
ENSTA-U2IS-AI/torch-uncertainty community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Mixup src/torch_uncertainty/transforms/mixup.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 0d567415bc4684f0 · report fixture: signature x:Tensor/2/float, y:Tensor/1/int, feats:NoneType/0/?, warp_param:NoneType/0/? · returned tuple · level recorded 2026-09-22
OFRIN/Tensorflow_MixUp community (archive-listed) 1 sample, 0 ran · 1 unverified
MixUp Train_MixUp.py unverified no licence file found · pointer only · cfc01e12143b4410 · report
jankrepl/mildlyoverfitted community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MLPClassifierMixup github_adventures/mixup/utils.py ran fingerprinted MIT (permissive) · 044377f3db8fca77 · report fixture: returned MLPClassifierMixup · level recorded 2026-09-22
pytorch/vision community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RandomMixUp references/classification/transforms.py ran BSD-3-Clause (permissive) · fa87b05b59895a9b · report fixture: signature batch:Tensor/4/float, target:Tensor/1/int · returned tuple · level recorded 2026-09-24
wangermeng2021/FastClassification community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Mixup augment/mixup.py ran MIT (permissive) · 8f549c9a18e67058 · report fixture: returned Mixup · 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.

26 assemblies on this paper: 26 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

26 sibling assemblies for mixup (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 26 sibling assemblies; the other 14 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. RandomMixUp entry · level 1 · ran · fa87b05b59895a9b

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. mixup_data entry · level 1 · ran; the contract check could not run (RAISES) · c8f7fd47a7acbaa3

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. DatasetRetriever entry · level 1 · ran · 7c45621d4018ce63

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. Mixup entry · level 1 · ran · 8f549c9a18e67058

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. mixup_data entry · level 1 · ran; the contract check could not run (RAISES) · 1905009bf59716f6

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. debug_mixup entry · level 0 · unverified · 9479dbe678007bc9
  2. BengaliMixUpDataset data_transform · level 1 · ran · eda27e400dd33e72
  3. get_augmenter helper · level 1 · ran; the contract check could not run · 5d040cba7a3612d3
  4. BengaliDataset helper · level 1 · ran · 5c69813c92b3303b
  5. crop_resize helper · level 1 · ran; the contract check could not run · 7406ca7275b897ae
  6. bbox helper · level 1 · ran · honoured contract · 7e848e7faedb674a

harvested Assembly for mixup (graph method: mixup). 3 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) · 1 unverified. The assembly has not been run end-to-end.

one of 26 siblings

  1. mixup entry · level 1 · ran; the contract check could not run (RAISES) · 656d88b7d9a9e392
  2. batch_shuffle_ddp helper · level 0 · unverified · d6b836d9b156da28
  3. concat_all_gather helper · level 1 · ran; the contract check could not run (RAISES) · fa052d95a1f73aa9

harvested Assembly for mixup (graph method: mixup). 2 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 26 siblings

  1. AddMixer entry · level 1 · ran · 60fc83929db77047
  2. get_random_sample helper · level 1 · ran · our draft was wrong · ff05773d89bd720b

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

one of 26 siblings

  1. mixup entry · level 0 · unverified · 9632c4d4a17cb9c6

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. mixup entry · level 1 · ran; the contract check could not run (RAISES) · bc9feed0a6523697

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

one of 26 siblings

  1. do_noisy_mixup entry · level 0 · unverified · e4a853c8450e16b2
  2. _noise helper · level 0 · unverified · 48b6ae3361582213

harvested Assembly for mixup (graph method: mixup). 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 26 siblings

  1. mixup_data entry · level 1 · ran; the contract check could not run (RAISES) · b062bea460457feb
  1. mixup · 78a0e9a9f9ae9fa7 · 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 · assemblies[12] in the JSON twin
  2. mixup · 86a2b400e93b2dc1 · 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[13] in the JSON twin
  3. mixup · 9267cf1841f7fe05 · 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[14] in the JSON twin
  4. MLPClassifierMixup · 9f4a20de9e000cde · 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 · assemblies[15] in the JSON twin
  5. mixup_data · abf550629cca9efc · 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[16] in the JSON twin
  6. mixup · b1c92f616fc1aae7 · 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[17] in the JSON twin
  7. MixUp · b3f291f14f2cf640 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. MixupTransform · c769959216959a0e · 7 bricks; individually on a fixture: 6 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; 6 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. do_mixup · c7d6730fb3811657 · 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 · assemblies[20] in the JSON twin
  10. Mixup · ca0a08735d996d28 · 2 bricks; 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. load_mixup_images_and_boxes · da467822c3525e7a · 3 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. MixAug · db841876baf709d1 · 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[23] in the JSON twin
  13. mixup_data · ed12d9dbbc855dfc · 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 · assemblies[24] in the JSON twin
  14. Mixup · f63b04bebe88f3f1 · 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[25] 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="1710.09412") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Domain GeneralizationImage ClassificationMemorizationOut-of-Distribution GeneralizationSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization ImageNet-A Mixup (ResNet-50) Top-1 accuracy % 6.6 #35 of 39 Archive leaderboard report
Image Classification CIFAR-10 DenseNet-BC-190 + Mixup Percentage correct 97.3 #87 of 265 Archive leaderboard report
Image Classification CIFAR-100 DenseNet-BC-190 + Mixup Percentage correct 83.20 #89 of 211 Archive leaderboard report
Image Classification Kuzushiji-MNIST PreActResNet-18 + Input Mixup Accuracy 98.41 #19 of 26 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 250 Labels MixUp Percentage error 47.43 #26 of 27 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 250 Labels MixUp Accuracy 60.03 #15 of 15 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: Mixup

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingMixupReLUResidual 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