A Novel Framework for Selection of GANs for an Application

02/20/2020

∙

Generative Adversarial Network (GAN) is a current focal point of research. The body of knowledge is fragmented, leading to a trial-error method while selecting an appropriate GAN for a given scenario. We provide a comprehensive summary of the evolution of GANs starting from its inception addressing issues like mode collapse, vanishing gradient, unstable training and non-convergence. We also provide a comparison of various GANs from the application point of view, its behaviour and implementation details. We propose a novel framework to identify candidate GANs for a specific use case based on architecture, loss, regularization and divergence. We also discuss application of the framework using an example, and we demonstrate a significant reduction in search space. This efficient way to determine potential GANs lowers unit economics of AI development for organizations.

READ FULL TEXT

A Novel Framework for Selection of GANs for an Application

Realizing GANs via a Tunable Loss Function

Stabilizing Generative Adversarial Network Training: A Survey

Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art

A Mathematical Introduction to Generative Adversarial Nets (GAN)

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization

On Convergence and Stability of GANs

A Novel Framework for Selection of GANs for an Application

Related Research

Realizing GANs via a Tunable Loss Function

Stabilizing Generative Adversarial Network Training: A Survey

Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art

A Mathematical Introduction to Generative Adversarial Nets (GAN)

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization

On Convergence and Stability of GANs