Margin Loss: Making Faces More Separable

The key point of face recognition is creating a discriminative feature representation to ensure intraclass compactness and interclass separability. Softmax loss is widely used in deep learning networks, but it is indirect for face verification. Center loss is effective to improve intraclass compactness, while interclass distances are ignored. In this letter, we propose a novel loss function, termed margin loss, to enlarge distances of interclass and reduce intraclass variations simultaneously. Margin loss aims to focus on samples hard to classify by a distance margin. Different from Softmax loss, margin loss is based on Euclidean distances that can directly measure face similarity. Experiments on different datasets have demonstrated the effectiveness of our method.

[1]  L. Deng,et al.  The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] , 2012, IEEE Signal Processing Magazine.

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

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

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

[5]  Lorenzo Rosasco,et al.  Are Loss Functions All the Same? , 2004, Neural Computation.

[6]  Bo Huang,et al.  Toward End-to-End Face Recognition Through Alignment Learning , 2017, IEEE Signal Processing Letters.

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

[8]  Erik Learned-Miller,et al.  Labeled Faces in the Wild : Updates and New Reporting Procedures , 2014 .

[9]  Yu Qiao,et al.  Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[12]  Christian Igel,et al.  A Unified View on Multi-class Support Vector Classification , 2016, J. Mach. Learn. Res..

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

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

[15]  Tieniu Tan,et al.  A Light CNN for Deep Face Representation With Noisy Labels , 2015, IEEE Transactions on Information Forensics and Security.

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

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

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

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

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

[21]  Jian Cheng,et al.  NormFace: L2 Hypersphere Embedding for Face Verification , 2017, ACM Multimedia.

[22]  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.

[23]  Ira Kemelmacher-Shlizerman,et al.  The MegaFace Benchmark: 1 Million Faces for Recognition at Scale , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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