Cristian Duguet, Adrian Hutter, Nandika Kalra, Arshak Navruzyan Overview Data augmentation of images is a widely adopted technique to improve models generalization [3] by applying transformations (or sets of combined transformations) during training and optionally at test time. Often practitioners look for the best set of transformations manually, either by relying on domain expertise or…Continue Reading “Automatically Finding Useful Augmentations with Minimal Use of Compute”