Discriminative Deep Metric Learning for Face Verification in the Wild

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 1875 - 1882
• Main Authors: Hu, Junlin, Lu, Jiwen, Tan, Yap-Peng
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Computer vision; Conferences; Deep Learning; Face; Face Verification; Feature extraction; Learning; Learning systems; Measurement; Metric Learning; Networks; Neural networks; Pattern recognition; Thresholds; Training; Trains; Transformations; Vectors; Videos
• DOI: 10.1109/CVPR.2014.242
• ISSN: 1063-6919

This paper presents a new discriminative deep metric learning (DDML) method for face verification in the wild. Different from existing metric learning-based face verification methods which aim to learn a Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, simultaneously, the proposed DDML trains a deep neural network which learns a set of hierarchical nonlinear transformations to project face pairs into the same feature subspace, under which the distance of each positive face pair is less than a smaller threshold and that of each negative pair is higher than a larger threshold, respectively, so that discriminative information can be exploited in the deep network. Our method achieves very competitive face verification performance on the widely used LFW and YouTube Faces (YTF) datasets.