Image Data Augmentation


Introduced by Cubuk et al. in AutoAugment: Learning Augmentation Policies from Data

AutoAugment is an automated approach to find data augmentation policies from data. It formulates the problem of finding the best augmentation policy as a discrete search problem. It consists of two components: a search algorithm and a search space.

At a high level, the search algorithm (implemented as a controller RNN) samples a data augmentation policy $S$, which has information about what image processing operation to use, the probability of using the operation in each batch, and the magnitude of the operation. The policy $S$ is used to train a neural network with a fixed architecture, whose validation accuracy $R$ is sent back to update the controller. Since $R$ is not differentiable, the controller will be updated by policy gradient methods.

The operations used are from PIL, a popular Python image library: all functions in PIL that accept an image as input and output an image. It additionally uses two other augmentation techniques: Cutout and SamplePairing. The operations searched over are ShearX/Y, TranslateX/Y, Rotate, AutoContrast, Invert, Equalize, Solarize, Posterize, Contrast, Color, Brightness, Sharpness, Cutout and Sample Pairing.

Source: AutoAugment: Learning Augmentation Policies from Data


Paper Code Results Date Stars