Methods › Computer Vision › Image Data Augmentation › Mixup

Mixup

651 papers tagged archive 2025-07-28

Introduced by Hongyi Zhang et al. in mixup: Beyond Empirical Risk Minimization

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels: (xᵢ, yᵢ), (xⱼ, yⱼ), a synthetic training example (x̂, ŷ) is generated as:

x̂ = λxᵢ + (1 − λ)xⱼ ŷ = λyᵢ + (1 − λ)yⱼ

where λ∼Beta(α= 0.2) is independently sampled for each augmented example.

PaperSourceSee Code · facebookresearch/mixup-cifar10

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 71 in the graph, strongest link: official). The lookup matched 'mixup' ignoring case. This answer is about arXiv:1710.09412, the paper the archive credits with this method.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:1710.09412 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 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 (of 47 harvested samples) · 15 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 651 · with a code link: 308 · where Syntology ran a sample: 89 (74 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (89 of 651 tagged: 74 with a run with no instrument failure, 15 where every run was a failure of Syntology's instrument)

Page 1 of 7: papers 1 to 100 of 651, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 424 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Data Augmentation245
Image Classification84
Domain Adaptation66
image-classification63
Classification40
Contrastive Learning38
Representation Learning35
Unsupervised Domain Adaptation33
Transfer Learning32
Diversity28
Object Detection27
Semantic Segmentation27
General Classification25
Knowledge Distillation25
Domain Generalization23
object-detection22
Self-Supervised Learning21
Segmentation19
Text Classification17
Graph Classification16

Usage over time archive 2025-07-28

Papers per year tagged with Mixup: 2017 to 2025, peak 137 137 0 2017: 1 paper 2017 2018: 7 papers 2018 2019: 32 papers 2019 2020: 67 papers 2020 2021: 121 papers 2021 2022: 134 papers 2022 2023: 137 papers 2023 2024: 106 papers 2024 2025: 46 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (651 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Image Data Augmentation

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