.png){kind=icon}
.png){kind=icon}
Return
BO-Aug: learning data augmentation policies via Bayesian optimization
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-022-03790-z.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Data augmentation has been an essential technique to increase the amount and diversity of datasets, thus improving deep learning models. To pursue further performance, several automated data augmentation approaches have recently been proposed to find data augmentation policies automatically. However, there are still some key issues that deserve further exploration, i.e., a precise policy search space definition, the instructive policy evaluation method, and the low computational cost of policy search. In this paper, we propose a novel method named BO-Aug that attempts to solve the above issues. Empirical verification on three widely used image classification datasets shows that the proposed method can achieve state-of-the-art or comparable performance compared with advanced automated data augmentation methods, with a relatively low cost. Our code is available at https://github.com/Zhangcx19/BO-Aug.
Keywords:
Data augmentation
Bayesian optimization
Neural network