.png){kind=icon}
返回
Regularizing Label-Augmented Generative Adversarial Networks Under Limited Data
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3259066.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Training generative adversarial networks (GANs) using limited training data is challenging since the original discriminator is prone to overfitting. The recently proposed label augmentation technique complements categorical data augmentation approaches for discriminator, showing improved data efficiency in training GANs but lacks a theoretical basis. In this paper, we propose a novel regularization approach for the label-augmented discriminator to further improve the data efficiency of training GANs with a theoretical basis. Specifically, the proposed regularization adaptively constrains the predictions of the label-augmented discriminator on generated data to be close to the moving averages of its historical predictions on real data, and vice versa. We theoretically establish a connection between the objective function with the proposed regularization and a f-divergence that is more robust than the previous reversed Kullback-Leibler divergence. Experimental results on various datasets and diverse architectures show the significantly improved data efficiency of our proposed method compared to state-of-the-art data-efficient GAN training approaches for training GANs under limited training data regimes.
Keyword:
Generative adversarial networks
Generators
Data augmentation
Training data
Task analysis
Self-supervised learning
Linear programming
Image generation
limited data
adaptive regularization
label augmentation
data augmentation
self-supervised learning
image generation
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Changes in the Microbiome Profile in Different Parts of the Intestine in Piglets with Diarrhea.png)
AnimalsOAAI
AnimalsIF0
OAAI分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏分享收藏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
查看更多内容