Validating Seed Data Samples for Synthetic Identities – Methodology and Uniqueness Metrics

Validating Seed Data Samples for Synthetic Identities – Methodology and Uniqueness Metrics

This work explores the identity attribute of synthetic face samples derived from Generative Adversarial Networks. The goal is to determine if individual samples are unique in terms of identity, firstly with respect to the seed dataset that trains the GAN model and secondly with respect to other synt...

Full description

Bibliographic Details
Main Authors: Viktor Varkarakis, Shabab Bazrafkan, Gabriel Costache, Peter Corcoran
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Artificial intelligence
computer vision
face recognition
generative adversarial networks (GANs)
StyleGAN
synthetic face
Online Access:https://ieeexplore.ieee.org/document/9165737/

Internet

https://ieeexplore.ieee.org/document/9165737/

Similar Items