Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model

Generative adversarial networks (GANs) generate photorealistic faces that are often indistinguishable by humans from real faces. While biases in machine learning models are often assumed to be due to biases in training data, we find pathological internal color and luminance biases in the discriminat...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-08
Hauptverfasser:	Grissom, Alvin, Lei, Ryan F, Gusdorff, Matt, Jeova Farias Sales Rocha Neto, Bailey, Lin, Trotter, Ryan
Format:	Artikel
Sprache:	eng
Schlagworte:	Bias Discriminators Generative adversarial networks Race
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!