Papers › AutoMix: Unveiling the Power of Mixup for Stronger Classifiers

AutoMix: Unveiling the Power of Mixup for Stronger Classifiers

24 Mar 2021arXiv:2103.13027archive 2025-07-28

Zicheng Liu, Siyuan Li, Di wu, Zihan Liu, ZhiYuan Chen, Lirong Wu, Stan Z. Li

Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency information to match the mixed samples and labels via complex offline optimization. However, there arises a trade-off between precise mixing policies and optimization complexity. To address this challenge, we propose a novel automatic mixup (AutoMix) framework, where the mixup policy is parameterized and serves the ultimate classification goal directly. Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i.e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework. For the generation, a learnable lightweight mixup generator, Mix Block, is designed to generate mixed samples by modeling patch-wise relationships under the direct supervision of the corresponding mixed labels. To prevent the degradation and instability of bi-level optimization, we further introduce a momentum pipeline to train AutoMix in an end-to-end manner. Extensive experiments on nine image benchmarks prove the superiority of AutoMix compared with state-of-the-art in various classification scenarios and downstream tasks.

PaperPDFCodeCode Syntology ran

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 (Westlake-AI/openmixup) is linked to this paper; the 6 samples below come from 2 community repositories. Syntology harvested code from Westlake-AI/openmixup for 4 other papers.

Westlake-AI/openmixup: 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), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 6 code samples harvested from 2 repositories linked to this paper: 4 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; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 2 repositories, 4 ran (1 with no instrument failure; 3 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 1 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.

Westlake-AI/openmixup officialmentioned in papermentioned 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), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
Westlake-AI/AutoMix mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
zeyuanyin/tiny-imagenet mentioned on GitHubpytorchMITSyntology: 5 samples, 4 ran (3 instrument-failed) · 1 unverified report

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

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

6 samples harvested: 4 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; 3 where Syntology's instrument failed) · 2 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 · our draft was wrong
1ran; the contract check could not run
1ran
2unverified

Licence: 3 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 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”. “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.

Westlake-AI/AutoMix community (archive-listed) 1 sample, 0 ran · 1 unverified
evaluate in 514 papers engine.py unverified Apache-2.0 (permissive) · 30d82c52aa52dbd7 · report
zeyuanyin/tiny-imagenet community (archive-listed) 5 samples, 4 ran (3 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
classification/utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · 0d95e28fac98427f · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-22
find_classes in 61 papers classification/tiny_imagenet_dataset.py ran · our draft was wrong MIT (permissive) · 403277d0bfbb477b · report fixture: signature class_file:str/0/str · returned tuple · level recorded 2026-09-24
make_dataset in 144 papers classification/tiny_imagenet_dataset.py ran MIT (permissive) · 5ded0879a886f3c4 · report fixture: signature root:str/0/str, base_folder:str/0/str, dirname:str/0/str, class_to_idx:dict/0/? · returned list · level recorded 2026-09-24
store_model_weights in 5 papers classification/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · aa2ba35b3854fa14 · report fixture: signature model:callable/0/?, checkpoint_path:str/0/str, checkpoint_key:str/0/str, strict:bool/0/bool · returned str · level recorded 2026-09-22
average_checkpoints in 21 papers classification/utils.py unverified MIT (permissive) here; the stored copy is pointer only · 30862aa4330bfa12 · report

Tasks

ClassificationData AugmentationGeneral ClassificationImage ClassificationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 ResNeXt-50 (AutoMix) Percentage correct 97.84 #68 of 265 Archive leaderboard report
Image Classification CIFAR-100 WRN-28-8 +AutoMix Percentage correct 85.16 #67 of 211 Archive leaderboard report
Image Classification CIFAR-100 ResNeXt-50(32x4d) + AutoMix Percentage correct 83.64 #85 of 211 Archive leaderboard report
Image Classification ImageNet ResNet-101 (AutoMix) Number of params 44.6M #671 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-101 (AutoMix) Top 1 Accuracy 80.98% #671 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-50 (AutoMix) Number of params 25.6M #767 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-50 (AutoMix) Top 1 Accuracy 79.25% #767 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-34 (AutoMix) Number of params 21.8M #925 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-34 (AutoMix) Top 1 Accuracy 76.1% #925 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-18 (AutoMix) Number of params 11.7M #1001 of 1060 Archive leaderboard report
Image Classification ImageNet ResNet-18 (AutoMix) Top 1 Accuracy 72.05% #1001 of 1060 Archive leaderboard report
Image Classification Places205 AutoMix (ResNet-50 Supervised) Top 1 Accuracy 64.1 #8 of 15 Archive leaderboard report
Image Classification Tiny ImageNet Classification ResNeXt-50 (AutoMix) Validation Acc 70.72% #15 of 23 Archive leaderboard report
Image Classification Tiny ImageNet Classification ResNet18 (AutoMix) Validation Acc 67.33% #20 of 23 Archive leaderboard report
Image Classification iNaturalist 2018 ResNeXt-101 (AutoMix) Top-1 Accuracy 70.49% #37 of 60 Archive leaderboard report
Image Classification iNaturalist 2018 ResNet-50 (AutoMix) Top-1 Accuracy 64.73% #49 of 60 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

AttentionLinear LayerMixupMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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