A Lightened CNN for Deep Face Representation

Convolution neural network (CNN) has significantly pushed forward the development of face recognition techniques. To achieve ultimate accuracy, CNN models tend to be deeper or multiple local facial patch ensemble, which result in a waste of time and space. To alleviate this issue, this paper studies a lightened CNN framework to learn a compact embedding for face representation. First, we introduce the concept of maxout in the fully connected layer to the convolution layer, which leads to a new activation function, named Max-Feature-Map (MFM). Compared with widely used ReLU, MFM can simultaneously capture compact representation and competitive information. Then, one shallow CNN model is constructed by 4 convolution layers and totally contains about 4M parameters; and the other is constructed by reducing the kernel size of convolution layers and adding Network in Network (NIN) layers between convolution layers based on the previous one. These models are trained on the CASIA-WebFace dataset and evaluated on the LFW and YTF datasets. Experimental results show that the proposed models achieve state-of-the-art results. At the same time, a reduction of computational cost is reached by over 9 times in comparison with the released VGG model.

[1]  Xiaoou Tang,et al.  Surpassing Human-Level Face Verification Performance on LFW with GaussianFace , 2014, AAAI.

[2]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[3]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[4]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[5]  Yuning Jiang,et al.  Learning Deep Face Representation , 2014, ArXiv.

[6]  Yoshua Bengio,et al.  Maxout Networks , 2013, ICML.

[7]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[8]  Xiaogang Wang,et al.  Deep Learning Face Representation by Joint Identification-Verification , 2014, NIPS.

[9]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[10]  Ming Yang,et al.  DeepFace: Closing the Gap to Human-Level Performance in Face Verification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[12]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[13]  Xiaogang Wang,et al.  Deep Learning Face Representation from Predicting 10,000 Classes , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Xiaogang Wang,et al.  Deep Convolutional Network Cascade for Facial Point Detection , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Chang Huang,et al.  Targeting Ultimate Accuracy: Face Recognition via Deep Embedding , 2015, ArXiv.

[16]  Jiwen Lu,et al.  Discriminative Deep Metric Learning for Face Verification in the Wild , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Shengcai Liao,et al.  Learning Face Representation from Scratch , 2014, ArXiv.

[18]  Dumitru Erhan,et al.  Scalable, High-Quality Object Detection , 2014, ArXiv.

[19]  Anil K. Jain,et al.  Unconstrained Face Recognition: Identifying a Person of Interest From a Media Collection , 2014, IEEE Transactions on Information Forensics and Security.

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[22]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[23]  Xiaogang Wang,et al.  Deeply learned face representations are sparse, selective, and robust , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Andrew Zisserman,et al.  Deep Face Recognition , 2015, BMVC.

[25]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jian Sun,et al.  Bayesian Face Revisited: A Joint Formulation , 2012, ECCV.

[27]  Ming Yang,et al.  Web-scale training for face identification , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).