Stereotype-Free Classification of Fictitious Faces

by   Mohammadhossein Toutiaee, et al.
University of Georgia

Equal Opportunity and Fairness are receiving increasing attention in artificial intelligence. Stereotyping is another source of discrimination, which yet has been unstudied in literature. GAN-made faces would be exposed to such discrimination, if they are classified by human perception. It is possible to eliminate the human impact on fictitious faces classification task by the use of statistical approaches. We present a novel approach through penalized regression to label stereotype-free GAN-generated synthetic unlabeled images. The proposed approach aids labeling new data (fictitious output images) by minimizing a penalized version of the least squares cost function between realistic pictures and target pictures.


page 5

page 6


Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights

Sophisticated generative adversary network (GAN) models are now able to ...

More Real than Real: A Study on Human Visual Perception of Synthetic Faces

Deep fakes became extremely popular in the last years, also thanks to th...

A Study of the Human Perception of Synthetic Faces

Advances in face synthesis have raised alarms about the deceptive use of...

An Introduction to Artificial Intelligence and Solutions to the Problems of Algorithmic Discrimination

There is substantial evidence that Artificial Intelligence (AI) and Mach...

Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Training

Training Generative adversarial networks (GANs) stably is a challenging ...

Fighting deepfakes by detecting GAN DCT anomalies

Synthetic multimedia content created through AI technologies, such as Ge...

BLADERUNNER: Rapid Countermeasure for Synthetic (AI-Generated) StyleGAN Faces

StyleGAN is the open-sourced TensorFlow implementation made by NVIDIA. I...

Please sign up or login with your details

Forgot password? Click here to reset