theoretical loss
Recently Published Documents


TOTAL DOCUMENTS

6
(FIVE YEARS 1)

H-INDEX

3
(FIVE YEARS 0)

Entropy ◽  
2021 ◽  
Vol 23 (9) ◽  
pp. 1231
Author(s):  
Xiangde Zhang ◽  
Jian Zhang

Mode collapse has always been a fundamental problem in generative adversarial networks. The recently proposed Zero Gradient Penalty (0GP) regularization can alleviate the mode collapse, but it will exacerbate a discriminator’s misjudgment problem, that is the discriminator judges that some generated samples are more real than real samples. In actual training, the discriminator will direct the generated samples to point to samples with higher discriminator outputs. The serious misjudgment problem of the discriminator will cause the generator to generate unnatural images and reduce the quality of the generation. This paper proposes Real Sample Consistency (RSC) regularization. In the training process, we randomly divided the samples into two parts and minimized the loss of the discriminator’s outputs corresponding to these two parts, forcing the discriminator to output the same value for all real samples. We analyzed the effectiveness of our method. The experimental results showed that our method can alleviate the discriminator’s misjudgment and perform better with a more stable training process than 0GP regularization. Our real sample consistency regularization improved the FID score for the conditional generation of Fake-As-Real GAN (FARGAN) from 14.28 to 9.8 on CIFAR-10. Our RSC regularization improved the FID score from 23.42 to 17.14 on CIFAR-100 and from 53.79 to 46.92 on ImageNet2012. Our RSC regularization improved the average distance between the generated and real samples from 0.028 to 0.025 on synthetic data. The loss of the generator and discriminator in standard GAN with our regularization was close to the theoretical loss and kept stable during the training process.


2015 ◽  
Vol 32 (3) ◽  
pp. 865-875 ◽  
Author(s):  
Matthew A. Tom ◽  
Howard J. Shaffer

2014 ◽  
Vol 1070-1072 ◽  
pp. 835-838
Author(s):  
Xiao Hui Liu ◽  
Hai Ou Yan ◽  
He He ◽  
Lin Ma ◽  
Yu Cheng ◽  
...  

A new development technique or method of graphical distribution network theoretical loss calculation software which based on Visio is presented in this paper. The software not only uses the graphical functions of Visio, but also fundamentally overcome the serious shortage of the Microsoft Visio VBA, it makes the drawing program in power system application software from the traditional VBA model to the embedded mode, and it can achieve the real time control of graphical distribution network theoretical loss calculation software. The study and applications show that this technical innovation gives a new effective approach for the development of graphical power system application software.


2012 ◽  
Vol 16 (5) ◽  
pp. 269-273 ◽  
Author(s):  
Michael Auer ◽  
Andreas Schneeberger ◽  
Mark D. Griffiths

Sign in / Sign up

Export Citation Format

Share Document