Fast AutoAugment
This work addresses the efficiency problem for researchers and practitioners using automated data augmentation in deep learning, offering a faster alternative to AutoAugment with similar results.
The paper tackles the high computational cost of AutoAugment's data augmentation policy search by proposing Fast AutoAugment, which uses a density matching strategy to reduce search time by orders of magnitude while achieving comparable performance on image recognition tasks like CIFAR-10, CIFAR-100, SVHN, and ImageNet.
Data augmentation is an essential technique for improving generalization ability of deep learning models. Recently, AutoAugment has been proposed as an algorithm to automatically search for augmentation policies from a dataset and has significantly enhanced performances on many image recognition tasks. However, its search method requires thousands of GPU hours even for a relatively small dataset. In this paper, we propose an algorithm called Fast AutoAugment that finds effective augmentation policies via a more efficient search strategy based on density matching. In comparison to AutoAugment, the proposed algorithm speeds up the search time by orders of magnitude while achieves comparable performances on image recognition tasks with various models and datasets including CIFAR-10, CIFAR-100, SVHN, and ImageNet.