.png){kind=icon}
返回
Closed-Loop Training for Projected GAN
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2023.3337711.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Projected GAN, a pre-trained GAN, has been found to perform well in generating images with only a few training samples. However, it struggles with extended training, which may lead to decreased performance over time. This is because the pre-trained discriminator consistently surpasses the generator, creating an unstable training environment. In this work, we propose a solution to this issue by introducing closed-loop control (CLC) into the dynamics of Projected GAN, stabilizing training, and improving generation performance. Our proposed method consistently reduces the Frechet Inception Distance (FID) of the previous methods; for example, it reduces the FID of Projected GAN by 4.31 on the Obama dataset. Our finding is fundamental and can be used in other pre-trained GANs.
Keyword:
Generative adversarial networks
Training
Transfer functions
Feature extraction
Generators
Image synthesis
Frequency-domain analysis
control theory
few-shot image generation
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
暂无机构信息
引用论文
ARVino - outdoor augmented reality visualisation of viticulture GIS dataARVino-葡萄栽培GIS数据的户外增强现实可视化
OAAI
.png){kind=icon}
OAAI分享收藏Semisupervised and Weakly Supervised Road Detection Based on Generative Adversarial Networks基于生成对抗网络的半监督和弱监督道路检测
PREAI
分享收藏分享收藏
查看更多内容