pith. sign in

arxiv: 2005.02157 · v1 · pith:P5NTGGE5new · submitted 2020-04-29 · 💻 cs.CV · cs.LG· stat.ML

Stereotype-Free Classification of Fictitious Faces

classification 💻 cs.CV cs.LGstat.ML
keywords facesfictitiousapproachclassificationdiscriminationhumanimagespenalized
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.