Out-of-Distribution Detection for Reliable Face Recognition

In real applications, face recognition systems are always faced with non-face inputs and low-quality faces due to the complicated conditions like mis-detections by face detectors. However, in deep learning based methods, these outliers are always ignored during training phase and the models tend to...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE signal processing letters 2020, Vol.27, p.710-714
Hauptverfasser:	Yu, Chang, Zhu, Xiangyu, Lei, Zhen, Li, Stan Z.
Format:	Artikel
Sprache:	eng
Schlagworte:	Detectors Face Face recognition Facial recognition technology Feature extraction low-quality Machine learning non-face out-of-distribution detection Outliers (statistics) Performance enhancement Testing Training Uncertainty
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!