Deep Learning Face Representation from Predicting 10,000 Classes

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1891 - 1898
• Main Authors: Sun, Yi, Wang, Xiaogang, Tang, Xiaoou
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Activation; Bayes methods; Biological neural networks; Classifiers; Computer vision; deep learning; Face; face verification; Feature extraction; Joints; Learning; Neurons; Pattern recognition; Representations; Tasks; Training

This paper proposes to learn a set of high-level feature representations through deep learning, referred to as Deep hidden IDentity features (DeepID), for face verification. We argue that DeepID can be effectively learned through challenging multi-class face identification tasks, whilst they can be...