Learning data augmentation policies using augmented random search
This work improves automated data augmentation for computer vision tasks, but it is incremental as it builds directly on AutoAugment.
The paper tackled the problem of sub-optimal data augmentation policies in AutoAugment by using Augmented Random Search to shift from a discrete to a continuous search space, achieving state-of-the-art accuracies on CIFAR-10, CIFAR-100, and ImageNet without additional data.
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.