When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
This work addresses the lack of reproducible and comparative analysis in CNN-based face recognition, providing insights for researchers in computer vision, though it is incremental as it builds on existing methods with new evaluations.
The authors tackled the problem of understanding why and how Convolutional Neural Networks (CNNs) work well for face recognition by conducting an extensive evaluation on the public LFW dataset, proposing three new CNN architectures trained on LFW and identifying key factors like feature dimensionality reduction and metric learning that maintain accuracy.
Deep learning, in particular Convolutional Neural Network (CNN), has achieved promising results in face recognition recently. However, it remains an open question: why CNNs work well and how to design a 'good' architecture. The existing works tend to focus on reporting CNN architectures that work well for face recognition rather than investigate the reason. In this work, we conduct an extensive evaluation of CNN-based face recognition systems (CNN-FRS) on a common ground to make our work easily reproducible. Specifically, we use public database LFW (Labeled Faces in the Wild) to train CNNs, unlike most existing CNNs trained on private databases. We propose three CNN architectures which are the first reported architectures trained using LFW data. This paper quantitatively compares the architectures of CNNs and evaluate the effect of different implementation choices. We identify several useful properties of CNN-FRS. For instance, the dimensionality of the learned features can be significantly reduced without adverse effect on face recognition accuracy. In addition, traditional metric learning method exploiting CNN-learned features is evaluated. Experiments show two crucial factors to good CNN-FRS performance are the fusion of multiple CNNs and metric learning. To make our work reproducible, source code and models will be made publicly available.