
Improved deep face identification with multi‐class pairwise discriminant loss
Author(s) -
Choi J.Y.
Publication year - 2017
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2017.2108
Subject(s) - softmax function , discriminative model , artificial intelligence , pattern recognition (psychology) , computer science , pairwise comparison , feature extraction , convolutional neural network , deep learning , face (sociological concept) , linear discriminant analysis , facial recognition system , feature (linguistics) , identification (biology) , discriminant , social science , linguistics , philosophy , botany , sociology , biology
A novel method to extract discriminative deep feature representations of facial images for face identification is presented. A new ‘multi‐class pairwise discriminant loss’ is devised and incorporated it into the general deep convolutional neural network learning framework in a novel way, leading to highly discriminative deep face features. The method shows significant improvement over existing deep feature extraction techniques relying on softmax or triplet loss. Moreover, the method achieves a level of accuracy on the widely used identification protocols, which are better and comparable results than other state‐of‐the‐art methods.