A Novel Framework for Selection of GANs for an Application
This work addresses the fragmented knowledge and trial-and-error methods in GAN selection, potentially lowering AI development costs for organizations.
The authors tackled the problem of selecting appropriate Generative Adversarial Networks (GANs) for specific applications by proposing a novel framework based on architecture, loss, regularization, and divergence, which significantly reduces the search space for candidate GANs.
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.