GA3N: Generative adversarial AutoAugment network

作者：

Highlights：

• Proposing a new adversarial AutoAugment framework with several GANs.

• Integrating two adversarial learning approaches for hard and synthetic samples.

• Presenting two different methods for constructing policy search space.

• Presenting distinct improvement compared with recent AutoAugment methods.

摘要

•Proposing a new adversarial AutoAugment framework with several GANs.•Integrating two adversarial learning approaches for hard and synthetic samples.•Presenting two different methods for constructing policy search space.•Presenting distinct improvement compared with recent AutoAugment methods.

论文关键词：Data augmentation,AutoAugment,Generative adversarial network,Classification,Deep learning,Adversarial learning

论文评审过程：Received 6 August 2021, Revised 3 January 2022, Accepted 7 March 2022, Available online 9 March 2022, Version of Record 20 March 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108637