3D-Aided Dual-Agent GANs for Unconstrained Face Recognition

Synthesizing realistic profile faces is beneficial for more efficiently training deep pose-invariant models for large-scale unconstrained face recognition, by augmenting the number of samples with extreme poses and avoiding costly annotation work. However, learning from synthetic faces may not achie...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2019-10, Vol.41 (10), p.2380-2394
Hauptverfasser:	Zhao, Jian, Xiong, Lin, Li, Jianshu, Xing, Junliang, Yan, Shuicheng, Feng, Jiashi
Format:	Artikel
Sprache:	eng
Schlagworte:	3D face model Annotations Coders Computer simulation Extreme values Face Face recognition Face synthesis Facial recognition technology Gallium nitride generative adversarial networks Generators Image resolution Learning Perception Realism Regularization Solid modeling Three dimensional models Three-dimensional displays Training unconstrained face recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!