Greedy AutoAugment
This work addresses the computational bottleneck in data augmentation search for neural networks, offering a more efficient method for practitioners.
The paper tackles the problem of efficiently searching for effective data augmentation policies by proposing Greedy AutoAugment, which reduces computational resource usage by 360 times while achieving better accuracy on datasets like Tiny ImageNet and CIFAR-10.
A major problem in data augmentation is to ensure that the generated new samples cover the search space. This is a challenging problem and requires exploration for data augmentation policies to ensure their effectiveness in covering the search space. In this paper, we propose Greedy AutoAugment as a highly efficient search algorithm to find the best augmentation policies. We use a greedy approach to reduce the exponential growth of the number of possible trials to linear growth. The Greedy Search also helps us to lead the search towards the sub-policies with better results, which eventually helps to increase the accuracy. The proposed method can be used as a reliable addition to the current artifitial neural networks. Our experiments on four datasets (Tiny ImageNet, CIFAR-10, CIFAR-100, and SVHN) show that Greedy AutoAugment provides better accuracy, while using 360 times fewer computational resources.