Online Hyper-Parameter Learning for Auto-Augmentation Strategy
Chen Lin, Minghao Guo, Chuming Li, Xin Yuan, Wei Wu, Junjie Yan, Dahua Lin, Wanli Ouyang
Abstract
Data augmentation is critical to the success of modern deep learning techniques. In this paper, we propose Online Hyper-parameter Learning for Auto-Augmentation (OHL-Auto-Aug), an economical solution that learns the augmentation policy distribution along with network training. Unlike previous methods on auto-augmentation that search augmentation strategies in an offline manner, our method formulates the augmentation policy as a parameterized probability distribution, thus allowing its parameters to be optimized jointly with network parameters. Our proposed OHL-Auto-Aug eliminates the need of re-training and dramatically reduces the cost of the overall search process, while establishes significantly accuracy improvements over baseline models. On both CIFAR-10 and ImageNet, our method achieves remarkable on search accuracy, 60x faster on CIFAR-10 and 24x faster on ImageNet, while maintaining competitive accuracies.
BibTeX
@inproceedings{iccv2019_onlinehyperparam,
title = {Online Hyper-Parameter Learning for Auto-Augmentation Strategy},
author = {Chen Lin and Minghao Guo and Chuming Li and Xin Yuan and Wei Wu and Junjie Yan and Dahua Lin and Wanli Ouyang},
booktitle = {ICCV 2019},
year = {2019}
}