Neural Architecture Search for Deep Face Recognition

By the widespread popularity of electronic devices, the emergence of biometric technology has brought significant convenience to user authentication compared with the traditional password and mode unlocking. Among many biological characteristics, the face is a universal and irreplaceable feature that does not need too much cooperation and can significantly improve the user's experience at the same time. Face recognition is one of the main functions of electronic equipment propaganda. Hence it's virtually worth researching in computer vision. Previous work in this field has focused on two directions: converting loss function to improve recognition accuracy in traditional deep convolution neural networks (Resnet); combining the latest loss function with the lightweight system (MobileNet) to reduce network size at the minimal expense of accuracy. But none of these has changed the network structure. With the development of AutoML, neural architecture search (NAS) has shown excellent performance in the benchmark of image classification. In this paper, we integrate NAS technology into face recognition to customize a more suitable network. We quote the framework of neural architecture search which trains child and controller network alternately. At the same time, we mutate NAS by incorporating evaluation latency into rewards of reinforcement learning and utilize policy gradient algorithm to search the architecture automatically with the most classical cross-entropy loss. The network architectures we searched out have got state-of-the-art accuracy in the large-scale face dataset, which achieves 98.77% top-1 in MS-Celeb-1M and 99.89% in LFW with relatively small network size. To the best of our knowledge, this proposal is the first attempt to use NAS to solve the problem of Deep Face Recognition and achieve the best results in this domain.

[1]  Xiao Zhang,et al.  Range Loss for Deep Face Recognition with Long-Tailed Training Data , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Shiv Ram Dubey,et al.  A Performance Comparison of Loss Functions for Deep Face Recognition , 2018, ArXiv.

[3]  Li Fei-Fei,et al.  Progressive Neural Architecture Search , 2017, ECCV.

[4]  Bo Chen,et al.  MnasNet: Platform-Aware Neural Architecture Search for Mobile , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[6]  Takayuki Okatani,et al.  On Deep Learning , 2015, Journal of the Robotics Society of Japan.

[7]  Zheru Chi,et al.  Facial Expression Recognition Based on Facial Components Detection and HOG Features , 2014 .

[8]  Raquel Urtasun,et al.  Graph HyperNetworks for Neural Architecture Search , 2018, ICLR.

[9]  Song Han,et al.  ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware , 2018, ICLR.

[10]  Yuxiao Hu,et al.  MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition , 2016, ECCV.

[11]  Liang Lin,et al.  SNAS: Stochastic Neural Architecture Search , 2018, ICLR.

[12]  Jian Cheng,et al.  Additive Margin Softmax for Face Verification , 2018, IEEE Signal Processing Letters.

[13]  Quoc V. Le,et al.  Efficient Neural Architecture Search via Parameter Sharing , 2018, ICML.

[14]  Qingquan Song,et al.  Efficient Neural Architecture Search with Network Morphism , 2018, ArXiv.

[15]  Li Fei-Fei,et al.  Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[17]  W. Marsden.  I and J , 2012 .

[18]  Yu Qiao,et al.  A Discriminative Feature Learning Approach for Deep Face Recognition , 2016, ECCV.

[19]  Xiaogang Wang,et al.  DeepID3: Face Recognition with Very Deep Neural Networks , 2015, ArXiv.

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

[21]  Stefanos Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Xing Ji,et al.  CosFace: Large Margin Cosine Loss for Deep Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Le Song,et al.  Learning towards Minimum Hyperspherical Energy , 2018, NeurIPS.

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

[25]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[26]  Gregory D. Hager,et al.  sharpDARTS: Faster and More Accurate Differentiable Architecture Search , 2019, ArXiv.

[27]  Shengcai Liao,et al.  Soft-Margin Softmax for Deep Classification , 2017, ICONIP.

[28]  Yiming Yang,et al.  DARTS: Differentiable Architecture Search , 2018, ICLR.

[29]  George Papandreou,et al.  Searching for Efficient Multi-Scale Architectures for Dense Image Prediction , 2018, NeurIPS.

[30]  Tal Hassner,et al.  Do We Really Need to Collect Millions of Faces for Effective Face Recognition? , 2016, ECCV.

[31]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[32]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Theodore Lim,et al.  SMASH: One-Shot Model Architecture Search through HyperNetworks , 2017, ICLR.

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

[35]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[36]  Alok Aggarwal,et al.  Regularized Evolution for Image Classifier Architecture Search , 2018, AAAI.

[37]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[38]  Shaogang Gong,et al.  Facial expression recognition based on Local Binary Patterns: A comprehensive study , 2009, Image Vis. Comput..

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

[40]  Quoc V. Le,et al.  DropBlock: A regularization method for convolutional networks , 2018, NeurIPS.

[41]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[42]  Tie-Yan Liu,et al.  Neural Architecture Optimization , 2018, NeurIPS.

[43]  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.

[44]  Amnon Shashua,et al.  Learning a Metric Embedding for Face Recognition using the Multibatch Method , 2016, NIPS.

[45]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

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

[48]  Wei Wu,et al.  BlockQNN: Efficient Block-Wise Neural Network Architecture Generation , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  Stefanos Zafeiriou,et al.  Marginal Loss for Deep Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).