MetaAugment: Sample-Aware Data Augmentation Policy Learning

Automated data augmentation has shown superior performance in image recognition. Existing works search for datasetlevel augmentation policies without considering individual sample variations, which are likely to be sub-optimal. On the other hand, learning different policies for different samples naively could greatly increase the computing cost. In this paper, we learn a sample-aware data augmentation policy efficiently by formulating it as a sample reweighting problem. Specifically, an augmentation policy network takes a transformation and the corresponding augmented image as inputs, and outputs a weight to adjust the augmented image loss computed by a task network. At training stage, the task network minimizes the weighted losses of augmented training images, while the policy network minimizes the loss of the task network on a validation set via meta-learning. We theoretically prove the convergence of the training procedure and further derive the exact convergence rate. Superior performance is achieved on widely-used benchmarks including CIFAR-10/100, Omniglot, and ImageNet.

Authors

• Fengwei Zhou Huawei Noah's Ark Lab
• Jiawei Li University of Science and Technology Beijing
• Chuanlong Xie Beijing Normal University
• Fei Chen
• Lanqing Hong Huawei Noah's Ark Lab
• Rui Sun Deep Space Exploration Laboratory, University of Science and Technology of China
• Zhenguo Li Huawei Noah's Ark Lab

Keywords

No keywords are indexed for this paper.