Improving Deep Learning with Generic Data Augmentation

Luke Taylor, Geoff Nitschke

Abstract: Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious.Data augmentationovercomes this issue by artificially inflating the training set with label preserving transformations. Recently there has been extensive use of generic data augmentation to improveConvolutional Neural Network(CNN) task performance. This study benchmarks various popular data augmentation schemes to allow researchers to make informed decisions as to which training methods are most appropriate for their data sets. Various geometric and photometric schemes are evaluated on a coarse-grained data set using a relatively simple CNN. Experimental results, run using 4-fold cross-validation and reported in terms of Top-1 and Top-5 accuracy, indicate that croppingin geometric augmentationsignificantly increases CNN task performance.