It is no secret amongst deep learning researchers that finding the optimal data augmentation strategy during training can mean the difference between state-of-the-art performance and a run-of-the-mill result. To that end, the community has seen many efforts to automate the process of finding the perfect augmentation procedure for any task at hand. Unfortunately, even recent cutting-edge methods bring massive computational overhead, requiring as many as 100 full model trainings to settle on an ideal configuration. We show how to achieve equivalent performance using just 6 trainings with Random Unidimensional Augmentation. Source code is available at https://github.com/fastestimator/RUA/tree/v1.0
@article{arxiv.2106.08756,
title = {Optimizing Data Augmentation Policy Through Random Unidimensional Search},
author = {Xiaomeng Dong and Michael Potter and Gaurav Kumar and Yun-Chan Tsai and V. Ratna Saripalli and Theodore Trafalis},
journal= {arXiv preprint arXiv:2106.08756},
year = {2023}
}