Classification with Dynamic Data Augmentation

Dejiang Xu, Mong-Li Lee, Wynne Hsu

Abstract: Data augmentation has improved the accuracy and robustness of deep neural networks. Research has focused on finding an optimal augmentation policy that generates good quality training images to improve classification accuracy. However, searching for this optimal augmentation policy is computationally expensive and is dependent on the neural architecture. In this work, we design a dynamic augmentation approach that automatically adjusts the number of transformation operations and their magnitudes during the training of deep neural networks. We also address the shift in the test data distribution by proposing to perform augmentation on the test data. We validate the effectiveness of our solution on CIFAR-10, CIFAR-100, ImageNet, and the perturbed datasets including CIFAR-10-C, CIFAR-100-C, ImageNet-A, ImageNet-C and ImageNet-P. Experiment results show that our proposed dynamic augmentation approach is scalable and gives good performances on clean, adversarial and corrupt datasets, reducing the best published results by a significant margin.