Reframing control methods for parameters optimization in adversarial image generation

Qamar Alfalouji

doi:10.1016/j.neunet.2022.06.015

Reframing control methods for parameters optimization in adversarial image generation

2022-09-01

1

PRE

AI

DOI：10.1016/j.neunet.2022.06.015

Original

Original request for help

Save

Abstract

En 中文

Training procedures for deep networks require the setting of several hyper-parameters that strongly affect the obtained results. The problem is even worse in adversarial learning strategies used for image generation where a proper balancing of the discriminative and generative networks is fundamental for an effective training. In this work we propose a novel hyper-parameters optimization strategy based on the use of Proportional-Integral (PI) and Proportional-Integral-Derivative (PID) controllers. Both open loop and closed loop schemes for the tuning of a single parameter or of multiple parameters together are proposed allowing an efficient parameter tuning without resorting to computationally demanding trial-and-error schemes. We applied the proposed strategies to the widely used BEGAN and CycleGAN models: They allowed to achieve a more stable training that converges faster. The obtained images are also sharper with a slightly better quality both visually and according to the FID and FCN metrics. Image translation results also showed better background preservation and less color artifacts with respect to CycleGAN. (c) 2022 Elsevier Ltd. All rights reserved.

Keywords:

Hyper-parameters optimization

GAN

Control methods

Reframing control methods for parameters optimization in adversarial image generation

Abstract

Journal

Organization