.png){kind=icon}
返回
An Automatic Control Perspective on Parameterizing Generative Adversarial Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2023.3267773.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This article presents a new perspective from control theory to interpret and solve the instability and mode collapse problems of generative adversarial networks (GANs). The dynamics of GANs are parameterized in the function space and control directed methods are applied to investigate GANs. First, the linear control theory is utilized to analyze and understand GANs. It is proved that the stability depends only on control parameters. Second, a proportional-integral-derivative (PID) controller is designed to improve its stability. GANs can be controlled to adaptively generate images by an overshoot rate that is only related to the PID control parameters. Third, a new PIDGAN is derived with a theoretical guarantee of stability. Fourth, to exploit the nonlinear characteristics of GANs, the nonlinear control theory is applied to further analyze GANs and develop a feedback linearization control-based PIDGAN named NPIDGAN. Both PIDGAN and NPIDGAN not only improve stability but also prevent mode collapse. With five datasets covering a wide variety of image domains, the proposed models achieve superior performance with 1024 $\times $ 1024 resolution compared with the state-of-the-art GANs, even when data are limited.
Keyword:
Training
Stability criteria
Control theory
Aerodynamics
Generative adversarial networks
Laplace equations
Aerospace electronics
data limited generation
generative adversarial network (GAN)
Index Terms
instability
mode collapse
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
暂无机构信息
引用论文
分享收藏
Removal of polyphenolic compounds from aqueous plant extracts using polyamide minicolumns.png)
IUBMB Life
OAAI
IUBMB LifeIF0
OAAI分享收藏The Routh-Hurwitz Stability Criterion, Revisited: The Case of Multiple Poles on Imaginary Axis重新审视routh-hurwitz稳定性准则: 虚轴上有多个极点的情况
PREAI
分享收藏Adaptive feedback linearization control of antilock braking systems using neural networksMECHATRONICS
MECHATRONICSIF3.1
PREAI
分享收藏
查看更多内容