Papers › AutoAugment: Learning Augmentation Strategies From Data

AutoAugment: Learning Augmentation Strategies From Data

1 Jun 2019CVPR 2019 6archive 2025-07-28

Ekin D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, Quoc V. Le

Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In this paper, we describe a simple procedure called AutoAugment to automatically search for improved data augmentation policies. In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch. A sub-policy consists of two operations, each operation being an image processing function such as translation, rotation, or shearing, and the probabilities and magnitudes with which the functions are applied. We use a search algorithm to find the best policy such that the neural network yields the highest validation accuracy on a target dataset. Our method achieves state-of-the-art accuracy on CIFAR-10, CIFAR-100, SVHN, and ImageNet (without additional data). On ImageNet, we attain a Top-1 accuracy of 83.5% which is 0.4% better than the previous record of 83.1%. On CIFAR-10, we achieve an error rate of 1.5%, which is 0.6% better than the previous state-of-the-art. Augmentation policies we find are transferable between datasets. The policy learned on ImageNet transfers well to achieve significant improvements on other datasets, such as Oxford Flowers, Caltech-101, Oxford-IIT Pets, FGVC Aircraft, and Stanford Cars.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

alililia/ascend_autoaugment mindsporeSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
yangyucheng000/gpu_autoaugment mindsporeSyntology: not harvested 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationDomain Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization VizWiz-Classification EfficientNet-B6 (autoaug) Accuracy - All Images 45.8 #13 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B6 (autoaug) Accuracy - Clean Images 50.7 #13 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B6 (autoaug) Accuracy - Corrupted Images 39.3 #13 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B5 (autoaug) Accuracy - All Images 45.7 #14 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B5 (autoaug) Accuracy - Clean Images 50.2 #14 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B5 (autoaug) Accuracy - Corrupted Images 39.8 #14 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B7 (autoaug) Accuracy - All Images 45 #16 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B7 (autoaug) Accuracy - Clean Images 49.9 #16 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B7 (autoaug) Accuracy - Corrupted Images 39.1 #16 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B4 (autoaug) Accuracy - All Images 44.3 #18 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B4 (autoaug) Accuracy - Clean Images 48.6 #18 of 90 Archive leaderboard report
Domain Generalization VizWiz-Classification EfficientNet-B4 (autoaug) Accuracy - Corrupted Images 38.2 #18 of 90 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

AutoAugmentLSTMSigmoid ActivationTanh Activation

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