Papers › AlignMixup: Improving Representations By Interpolating Aligned Features

AlignMixup: Improving Representations By Interpolating Aligned Features

29 Mar 2021CVPR 2022 1arXiv:2103.15375archive 2025-07-28

Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. Many recent mixup methods focus on cutting and pasting two or more objects into one image, which is more about efficient processing than interpolation. However, how to best interpolate images is not well defined. In this sense, mixup has been connected to autoencoders, because often autoencoders "interpolate well", for instance generating an image that continuously deforms into another. In this work, we revisit mixup from the interpolation perspective and introduce AlignMix, where we geometrically align two images in the feature space. The correspondences allow us to interpolate between two sets of features, while keeping the locations of one set. Interestingly, this gives rise to a situation where mixup retains mostly the geometry or pose of one image and the texture of the other, connecting it to style transfer. More than that, we show that an autoencoder can still improve representation learning under mixup, without the classifier ever seeing decoded images. AlignMix outperforms state-of-the-art mixup methods on five different benchmarks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2103.15375")

Code

Syntology Ran 3 of 8 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 8 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shashankvkt/alignmixup_cvpr22 officialmentioned in papermentioned on GitHubpytorchMIT report
Westlake-AI/openmixup mentioned on GitHubpytorch report

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

Code Syntology ran Syntology

8 samples harvested; 3 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
5unverified

Licence: 0 of the 8 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 shashankvkt/alignmixup_cvpr22. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

conv3x3 shashankvkt/alignmixup_cvpr22/imagenet/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
conv3x3 shashankvkt/alignmixup_cvpr22/cifar10_100/models/WideResnet.py official repository ran · our draft was wrong MIT (permissive) · 00e569acd6b45ef0 · report
conv3x3 shashankvkt/alignmixup_cvpr22/cifar10_100/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · 583f9780bdd00a45 · report
cosine_scheduler shashankvkt/alignmixup_cvpr22/imagenet/utils/util.py official repository unverified MIT (permissive) · 757642f60b4ddb4a · report
mixup_process shashankvkt/alignmixup_cvpr22/cifar10_100/models/resnet18_classifier.py official repository unverified MIT (permissive) · aa3f975a6414573b · report
subset_of_ImageNet_train_split shashankvkt/alignmixup_cvpr22/imagenet/utils/util.py official repository unverified MIT (permissive) · de7aea7428f71cf9 · report
wrn28_10 shashankvkt/alignmixup_cvpr22/cifar10_100/models/WideResnet.py official repository unverified MIT (permissive) · 1bcad658b2d372fc · report
wrn28_2 shashankvkt/alignmixup_cvpr22/cifar10_100/models/WideResnet.py official repository unverified MIT (permissive) · f971438664b96268 · report

Tasks

Data AugmentationRepresentation LearningStyle Transfer

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Representation Learning CIFAR10 Resnet 18 Accuracy (%) 97.05 #1 of 1 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

Mixup

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