Faster AutoAugment: Learning Augmentation Strategies Using Backpropagation

Autor: Kazuki Yoshizoe, Hideki Nakayama, Jan Zdenek, Ryuichiro Hataya
Rok vydání: 2020
Předmět:
Zdroj: Computer Vision – ECCV 2020 ISBN: 9783030585945
ECCV (25)
DOI: 10.1007/978-3-030-58595-2_1
Popis: Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms outperform hand-made strategies. Such methods employ black-box search algorithms over image transformations with continuous or discrete parameters and require a long time to obtain better strategies. In this paper, we propose a differentiable policy search pipeline for data augmentation, which is much faster than previous methods. We introduce approximate gradients for several transformation operations with discrete parameters as well as a differentiable mechanism for selecting operations. As the objective of training, we minimize the distance between the distributions of augmented and original data, which can be differentiated. We show that our method, Faster AutoAugment, achieves significantly faster searching than prior methods without a performance drop.
Databáze: OpenAIRE