FaceNet: A unified embedding for face recognition and clustering

• Published in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 815 - 823
• Main Authors: Schroff, Florian, Kalenichenko, Dmitry, Philbin, James
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2015
• Subjects: Accuracy; Artificial neural networks; Clustering; Computer vision; Conferences; Euclidean geometry; Face; Face recognition; Pattern recognition; Principal component analysis; Similarity; Tasks; Training
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2015.7298682

Despite significant recent advances in the field of face recognition [10, 14, 15, 17], implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity. Once this space has been produced, tasks such as face recognition, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings asfeature vectors. Our method uses a deep convolutional network trained to directly optimize the embedding itself, rather than an intermediate bottleneck layer as in previous deep learning approaches. To train, we use triplets of roughly aligned matching / non-matching face patches generated using a novel online triplet mining method. The benefit of our approach is much greater representational efficiency: we achieve state-of-the-artface recognition performance using only 128-bytes perface. On the widely used Labeled Faces in the Wild (LFW) dataset, our system achieves a new record accuracy of 99.63%. On YouTube Faces DB it achieves 95.12%. Our system cuts the error rate in comparison to the best published result [15] by 30% on both datasets.