Mis-classified Vector Guided Softmax Loss for Face Recognition

Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (e.g., angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our code is available at http://www.cbsr.ia.ac.cn/users/xiaobowang/.

[1]  Xiaogang Wang,et al.  Residual Attention Network for Image Classification , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Jian Wang,et al.  Deep Metric Learning with Angular Loss , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[4]  Shifeng Zhang,et al.  FaceBoxes: A CPU real-time face detector with high accuracy , 2017, 2017 IEEE International Joint Conference on Biometrics (IJCB).

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

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

[7]  Carlos D. Castillo,et al.  Frontal to profile face verification in the wild , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

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

[9]  Ira Kemelmacher-Shlizerman,et al.  Level Playing Field for Million Scale Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Xiangyu Zhu,et al.  Cross-Modality Face Recognition via Heterogeneous Joint Bayesian , 2017, IEEE Signal Processing Letters.

[11]  Danna Zhou,et al.  d. , 1934, Microbial pathogenesis.

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

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

[14]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[15]  Tao Mei,et al.  A High-Efficiency Framework for Constructing Large-Scale Face Parsing Benchmark , 2019, ArXiv.

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

[17]  Ming Tang,et al.  Learning Discriminative and Complementary Patches for Face Recognition , 2019, 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019).

[18]  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).

[19]  Shengcai Liao,et al.  A benchmark study of large-scale unconstrained face recognition , 2014, IEEE International Joint Conference on Biometrics.

[20]  Josef Kittler,et al.  Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[21]  Shifeng Zhang,et al.  Ensemble Soft-Margin Softmax Loss for Image Classification , 2018, IJCAI.

[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]  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]  Stan Z. Li,et al.  Adaptively Unified Semi-Supervised Dictionary Learning with Active Points , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[25]  Xiangyu Zhu,et al.  AdaptiveFace: Adaptive Margin and Sampling for Face Recognition , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Fei Wang,et al.  The Devil of Face Recognition is in the Noise , 2018, ECCV.

[27]  Weihong Deng,et al.  Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments , 2017, ArXiv.

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

[29]  Mei Wang,et al.  Racial Faces in-the-Wild: Reducing Racial Bias by Deep Unsupervised Domain Adaptation , 2018, ArXiv.

[30]  Shifeng Zhang,et al.  Support Vector Guided Softmax Loss for Face Recognition , 2018, ArXiv.

[31]  Abhinav Gupta,et al.  Training Region-Based Object Detectors with Online Hard Example Mining , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[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]  Yongxin Yang,et al.  Frankenstein: Learning Deep Face Representations Using Small Data , 2016, IEEE Transactions on Image Processing.

[35]  Stefanos Zafeiriou,et al.  AgeDB: The First Manually Collected, In-the-Wild Age Database , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[37]  Liu Hao,et al.  AdaptiveFace: Adaptive Margin and Sampling for Face Recognition , 2019 .

[38]  Hailin Shi,et al.  Co-Mining: Deep Face Recognition With Noisy Labels , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[39]  Weihong Deng,et al.  Cross-Pose LFW : A Database for Studying Cross-Pose Face Recognition in Unconstrained Environments , 2018 .

[40]  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).

[41]  Mei Wang,et al.  Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[42]  Haifeng Shen,et al.  Virtual Class Enhanced Discriminative Embedding Learning , 2018, NeurIPS.

[43]  Shifeng Zhang,et al.  Faceboxes: A CPU real-time and accurate unconstrained face detector , 2019, Neurocomputing.

[44]  Marios Savvides,et al.  Ring Loss: Convex Feature Normalization for Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[46]  Carlos D. Castillo,et al.  L2-constrained Softmax Loss for Discriminative Face Verification , 2017, ArXiv.

[47]  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.