Fast AutoAugment

by   Sungbin Lim, et al.
Kakao Corp.
Université de Montréal

Data augmentation is an indispensable technique to improve generalization and also to deal with imbalanced datasets. Recently, AutoAugment has been proposed to automatically search augmentation policies from a dataset and has significantly improved performances on many image recognition tasks. However, its search method requires thousands of GPU hours to train even in a reduced setting. In this paper, we propose Fast AutoAugment algorithm that learns augmentation policies using a more efficient search strategy based on density matching. In comparison to AutoAugment, the proposed algorithm speeds up the search time by orders of magnitude while maintaining the comparable performances on the image recognition tasks with various models and datasets including CIFAR-10, CIFAR-100, and ImageNet.


page 1

page 2

page 3

page 4


Meta Approach to Data Augmentation Optimization

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

Hypernetwork-Based Augmentation

Data augmentation is an effective technique to improve the generalizatio...

UniformAugment: A Search-free Probabilistic Data Augmentation Approach

Augmenting training datasets has been shown to improve the learning effe...

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

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

RangeAugment: Efficient Online Augmentation with Range Learning

State-of-the-art automatic augmentation methods (e.g., AutoAugment and R...

Improving Auto-Augment via Augmentation-Wise Weight Sharing

The recent progress on automatically searching augmentation policies has...

Please sign up or login with your details

Forgot password? Click here to reset