Learning data augmentation policies using augmented random search

Abstract

Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment searches for the augmentation polices in the discrete search space, which may lead to a sub-optimal solution. In this paper, we employ the Augmented Random Search method (ARS) to improve the performance of AutoAugment. Our key contribution is to change the discrete search space to continuous space, which will improve the searching performance and maintain the diversities between sub-policies. With the proposed method, state-of-the-art accuracies are achieved on CIFAR-10, CIFAR-100, and ImageNet (without additional data). Our code is available at https://github.com/gmy2013/ARS-Aug.

Submitted to ICASSP

References in corpus (9)

• mixup: Beyond Empirical Risk Minimization
• Wide Residual Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Random Erasing Data Augmentation
• Shake-Shake regularization
• Ray: A Distributed Framework for Emerging AI Applications
• ShakeDrop Regularization for Deep Residual Learning
• Simple random search provides a competitive approach to reinforcement learning

Cited by in corpus (3)

• AutoML: A Survey of the State-of-the-Art
• Simulating Content Consistent Vehicle Datasets with Attribute Descent
• Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning