Greedy AutoAugment

TL;DR

Greedy AutoAugment introduces an efficient greedy search algorithm for data augmentation policies, significantly reducing computational costs while improving accuracy across multiple datasets.

Contribution

It proposes a novel greedy search method that efficiently finds effective augmentation policies with linear complexity, outperforming existing approaches in accuracy and resource usage.

Findings

Achieves higher accuracy on four datasets.

Uses 360 times fewer computational resources.

Effective in guiding search towards better policies.

Abstract

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.