ParticleAugment: Sampling-based data augmentation

We present an automated data augmentation approach for image classification. formulate the problem as Monte Carlo sampling where our goal is to approximate optimal policies. propose a particle filtering formulation find policies and their schedules during model training. Our performance measurement procedure relies on validation subset of training set, while policy transition depends Gaussian prior optional velocity parameter. In experiments, we show that reaches promising results CIFAR-10, CIFAR-100, ImageNet datasets using standard network architectures this problem. By comparing with related work, also method balance between computational cost search performance.