.png){kind=icon}
返回
GA3N: Generative adversarial AutoAugment network
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108637.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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. (C) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Data augmentation
AutoAugment
Generative adversarial network
Classification
Deep learning
Adversarial learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Role of interfacial phenomena in the behavior of alumina-supported palladium crystallites in oxygen
.png){kind=icon}
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
分享收藏分享收藏Effective data generation for imbalanced learning using conditional generative adversarial networks使用条件生成对抗网络为不平衡学习有效生成数据
PREAI
分享收藏
查看更多内容