GA3N: Generative adversarial AutoAugment network

Vanchinbal Chinbat, Seung Hwan Bae

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Data augmentation is beneficial for improving robustness of deep meta-learning. However, data augmentation methods for the recent deep meta-learning are still based on photometric or geometric manipulations or combinations of images. This paper proposes a generative adversarial autoaugment network (GA3N) for enlarging the augmentation search space and improving classification accuracy. To achieve, we first extend the search space of image augmentation by using GANs. However, the main challenge is to generate images suitable for the task. For solution, we find the best policy by optimizing a target and GAN losses alternatively. We then use the manipulated and generated samples determined by the policy network as augmented samples for improving the target tasks. To show the effects of our method, we implement classification networks by combining our GA3N and evaluate them on CIFAR-100 and Tiny-ImageNet datasets. As a result, we achieve better accuracy than the recent AutoAugment methods on each dataset.

Original languageEnglish
Article number108637
JournalPattern Recognition
Volume127
DOIs
StatePublished - Jul 2022

Bibliographical note

Publisher Copyright:
© 2022 Elsevier Ltd

Keywords

  • Adversarial learning
  • AutoAugment
  • Classification
  • Data augmentation
  • Deep learning
  • Generative adversarial network

Fingerprint

Dive into the research topics of 'GA3N: Generative adversarial AutoAugment network'. Together they form a unique fingerprint.

Cite this