Methods › Computer Vision › Image Data Augmentation › AugMix
AugMix
Introduced by Dan Hendrycks et al. in AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
AugMix mixes augmented images through linear interpolations. Consequently it is like Mixup but instead mixes augmented versions of the same image.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 15 in the graph, strongest link: official). The lookup matched 'AUGMIX' ignoring case. This answer is about arXiv:1912.02781, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1912.02781 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 46 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 2 violated, 3 with no contract checked; 37 where Syntology's instrument failed) · 5 unverified (of 51 harvested samples) · 25 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.
Papers archive 2025-07-28
archive papers tagged: 20 · with a code link: 9 · where Syntology ran a sample: 5 (3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 20 tagged: 3 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 20 of 20, 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.
-
MediAug: Exploring Visual Augmentation in Medical Imaging 26 Apr 2025 · 1 repository · arXiv:2504.18983
-
Self-supervised Transformation Learning for Equivariant Representations 15 Jan 2025 · 1 repository · arXiv:2501.08712Syntology official (archive's flag): 3 ran · 3 ran (of which 2 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) · 0 unverified (of 3 harvested samples)
-
FedCCRL: Federated Domain Generalization with Cross-Client Representation Learning 15 Oct 2024 · 1 repository · arXiv:2410.11267
-
Dynamic Batch Norm Statistics Update for Natural Robustness 31 Oct 2023 · 0 repositories · arXiv:2310.20649
-
Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks 30 Jun 2023 · 1 repository · arXiv:2306.17630
-
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers 15 Jun 2023 · 0 repositories · arXiv:2306.09192
-
Impact of Light and Shadow on Robustness of Deep Neural Networks 23 May 2023 · 0 repositories · arXiv:2305.14165
-
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel 22 Feb 2023 · 0 repositories · arXiv:2302.11188
-
Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration 24 Feb 2022 · 0 repositories · arXiv:2202.12412
-
How to augment your ViTs? Consistency loss and StyleAug, a random style transfer augmentation 16 Dec 2021 · 0 repositories · arXiv:2112.09260
-
Benchmarks for Corruption Invariant Person Re-identification 1 Nov 2021 · 1 repository · arXiv:2111.00880Syntology official (archive's flag): 2 ran · 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 (of 2 harvested samples)
-
AugMax: Adversarial Composition of Random Augmentations for Robust Training 26 Oct 2021 · 1 repository · arXiv:2110.13771Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 2 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 19 harvested samples)
-
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining 29 Sep 2021 · 0 repositories · arXiv:2109.14707
-
Defending Against Image Corruptions Through Adversarial Augmentations 2 Apr 2021 · 0 repositories · arXiv:2104.01086
-
On the effectiveness of adversarial training against common corruptions 3 Mar 2021 · 1 repository · arXiv:2103.02325
-
A Deep Learning Approach for Diabetic Retinopathy detection using Transfer Learning 1 Jan 2021 · 0 repositories
-
What are effective labels for augmented data? Improving robustness with AutoLabel 1 Jan 2021 · 0 repositories
-
StackMix: A complementary Mix algorithm 25 Nov 2020 · 0 repositories · arXiv:2011.12618
-
Improving robustness against common corruptions by covariate shift adaptation 30 Jun 2020 · 2 repositories · arXiv:2006.16971Syntology official (archive's flag): 3 ran · 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) · 0 unverified (of 3 harvested samples)
-
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty 5 Dec 2019 · 15 repositories · arXiv:1912.02781Syntology official (archive's flag): 12 ran · 46 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 2 violated, 3 with no contract checked; 37 where Syntology's instrument failed) · 5 unverified (of 51 harvested samples) · 25 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 28 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
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
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