Authors:
Frederic Rizk
1
;
Rodrigue Rizk
2
;
Dominick Rizk
1
and
Chee-Hung Henry Chu
1
;
3
Affiliations:
1
The Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, U.S.A.
;
2
Department of Computer Science, University of South Dakota, Vemillion, SD, U.S.A.
;
3
Informatics Research Institute, University of Louisiana at Lafayette, Lafayette, LA, U.S.A.
Keyword(s):
Generative Adversarial Networks, GAN, Meta-Analysis, Latent Space, Data Augmentation.
Abstract:
Generative Adversarial Networks (GANs) are an emerging class of deep neural networks that has sparked
considerable interest in the field of unsupervised learning because of its exceptional data generation performance. Nevertheless, the GAN’s latent space that represents the core of these generative models has not been
studied in depth in terms of its effect on the generated image space. In this paper, we propose and evaluate
MAGAN, an algorithm for Meta-Analysis for GANs’ latent space. GAN-derived synthetic images are also
evaluated in terms of their efficiency in complementing the data training, where the produced output is employed for data augmentation, mitigating the labeled data scarcity. The results suggest that GANs may be used
as a parameter-controlled data generator for data-driven augmentation. The quantitative findings show that
MAGAN can correctly trace the relationship between the arithmetic adjustments in the latent space and their
effects on the output in the im
age space. We empirically determine the parameter ε for each class such that
the latent space is insensitive to a shift of ε×σ from the mean vector, where σ is the standard deviation of a
particular class.
(More)