Effect of Laplacian Smoothing Stochastic Gradient Descent with Angular Margin Softmax Loss on Face Recognition

An important task in deep learning for face recognition is to use proper loss functions and optimization technique. Several loss functions have been proposed using stochastic gradient descent for this task. The main purpose of this work is to propose the strategy to use the Laplacian smoothing stochastic gradient descent with combination of multiplicative angular margin to enhance the performance of angularly discriminative features of angular margin softmax loss for face recognition. The model is trained on a most popular face recognition dataset CASIA-WebFace and it achieves the state-of-the-art performance on several academic benchmark datasets such as Labeled Face in the Wild (LFW), YouTube Faces (YTF), VGGFace1 and VGGFace2. Our method achieves a new record accuracy of 99.54% on LFW dataset. On YTF dataset it achieves 95.53% accuracy.

[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]  Tong Zhang,et al.  Accelerating Stochastic Gradient Descent using Predictive Variance Reduction , 2013, NIPS.

[3]  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.

[4]  Yang Song,et al.  Learning Fine-Grained Image Similarity with Deep Ranking , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

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

[8]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[9]  Meng Yang,et al.  Large-Margin Softmax Loss for Convolutional Neural Networks , 2016, ICML.

[10]  Jian Sun,et al.  Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[13]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[14]  Jian Sun,et al.  Face recognition with learning-based descriptor , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

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

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

[17]  Chengjun Liu,et al.  Gabor feature based classification using the enhanced fisher linear discriminant model for face recognition , 2002, IEEE Trans. Image Process..

[18]  Francis Bach,et al.  SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives , 2014, NIPS.

[19]  Matti Pietikäinen,et al.  Face Description with Local Binary Patterns: Application to Face Recognition , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Stefano Soatto,et al.  Deep relaxation: partial differential equations for optimizing deep neural networks , 2017, Research in the Mathematical Sciences.

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

[22]  Nir Ailon,et al.  Deep Metric Learning Using Triplet Network , 2014, SIMBAD.

[23]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  William J. Christmas,et al.  When Face Recognition Meets with Deep Learning: An Evaluation of Convolutional Neural Networks for Face Recognition , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[25]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[27]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[28]  Omkar M. Parkhi,et al.  VGGFace2: A Dataset for Recognising Faces across Pose and Age , 2017, 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).

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

[30]  Jiwen Lu,et al.  PCANet: A Simple Deep Learning Baseline for Image Classification? , 2014, IEEE Transactions on Image Processing.

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

[32]  Xiangyang Xue,et al.  Multi-task Deep Neural Network for Joint Face Recognition and Facial Attribute Prediction , 2017, ICMR.

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

[34]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Tal Hassner,et al.  Face recognition in unconstrained videos with matched background similarity , 2011, CVPR 2011.

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