AutoAugment: Learning Augmentation Policies from Data

by   Ekin D. Cubuk, et al.

In this paper, we take a closer look at data augmentation for images, and describe a simple procedure called AutoAugment to search for improved data augmentation policies. Our key insight is to create a search space of data augmentation policies, evaluating the quality of a particular policy directly on the dataset of interest. 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 83.54 which is 0.65 settings, AutoAugment performs comparably to semi-supervised methods without using any unlabeled examples. Finally, policies learned from one dataset can be transferred to work well on other similar datasets. For example, the policy learned on ImageNet allows us to achieve state-of-the-art accuracy on the fine grained visual classification dataset Stanford Cars, without fine-tuning weights pre-trained on additional data.


page 3

page 7


Learning data augmentation policies using augmented random search

Previous attempts for data augmentation are designed manually, and the a...

Adversarial AutoAugment

Data augmentation (DA) has been widely utilized to improve generalizatio...

Meta Approach to Data Augmentation Optimization

Data augmentation policies drastically improve the performance of image ...

DNA: Dynamic Network Augmentation

In many classification problems, we want a classifier that is robust to ...

Exploiting Learned Policies in Focal Search

Recent machine-learning approaches to deterministic search and domain-in...

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

A key challenge in leveraging data augmentation for neural network train...

RandAugment: Practical data augmentation with no separate search

Recent work has shown that data augmentation has the potential to signif...

Please sign up or login with your details

Forgot password? Click here to reset