When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition

By Guosheng Hu, Yongxin Yang, Dong Yi, Josef Kittler, William J. Christmas, S. Li, Timothy M. Hospedales. 2015 IEEE International Conference on Computer Vision Workshop (ICCVW), 2015

331 citations recorded by the source corpus.

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 evaluates 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, a 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.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/a3cbdf7f87205b1808f62ae6676e2bbfa7847dde

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

CosFace: Large Margin Cosine Loss for Deep Face Recognition (2018, background): “Other approaches [41, 11] also prove the effectiveness of deep CNNs on face recognition.”
The MegaFace Benchmark: 1 Million Faces for Recognition at Scale (2015, background): “, [25, 28, 27, 29, 30] reported recognition rates above 99%+ [14] (better than human recognition rates estimated on the same dataset by [19]).”
Deep Learning on Image Denoising: An overview (2019, background): “Since 2014, deep networks have been widely used in real-world image applications, such as facial recognition [86] and medical diagnosis [124].”
Smart Regularization of Deep Architectures (2015, background): “We found that this could be easily fixed by adding a batch normalization layer [43] before the softmax layer.”
Rotation Equivariant Vector Field Networks (2016, methodology): “We have presented a new way of hard-coding rotation equivariance in CNNs by applying each ﬁlter at different orientations and extracting a vector ﬁeld feature map that encodes the maximum activation magnitude and angle.”
MegaFace: A Million Faces for Recognition at Scale (2015, background): “Indeed, just in the last few months a number of methods [23, 26, 25, 27, 28] reported recognition rates above 99%+ [12] (better than human recognition rates estimated on the same dataset by [16]).”