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

翻译：深度学习研究者皆知，在训练过程中找到最优数据增强策略可能意味着顶尖性能与普通结果之间的差别。为此，该领域已涌现大量自动化搜索最佳数据增强流程的努力。然而，即便是近年最新的方法仍带来巨大的计算开销，需要多达100次完整模型训练才能确定理想配置。我们证明，通过随机一维增强（Random Unidimensional Augmentation）仅需6次训练即可达到同等性能。源代码见 https://github.com/fastestimator/RUA/tree/v1.0