MagFace: A Universal Representation for Face Recognition and Quality Assessment

The performance of face recognition system degrades when the variability of the acquired faces increases. Prior work alleviates this issue by either monitoring the face quality in pre-processing or predicting the data uncertainty along with the face feature. This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face. Under the new loss, it can be proven that the magnitude of the feature embedding monotonically increases if the subject is more likely to be recognized. In addition, Mag-Face introduces an adaptive mechanism to learn a well-structured within-class feature distributions by pulling easy samples to class centers while pushing hard samples away. This prevents models from overfitting on noisy low-quality samples and improves face recognition in the wild. Extensive experiments conducted on face recognition, quality assessments as well as clustering demonstrate its superiority over state-of-the-arts. The code is available at https://github.com/IrvingMeng/MagFace.

[1]  Kuiyuan Yang,et al.  Feature Incay for Representation Regularization , 2018, ICLR.

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

[3]  Elham Tabassi,et al.  Performance of Biometric Quality Measures , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[6]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[7]  Dong Cao,et al.  Learning Meta Face Recognition in Unseen Domains , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[9]  Anil K. Jain,et al.  Learning Face Image Quality From Human Assessments , 2018, IEEE Transactions on Information Forensics and Security.

[10]  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).

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

[12]  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).

[13]  Anil K. Jain,et al.  IARPA Janus Benchmark - C: Face Dataset and Protocol , 2018, 2018 International Conference on Biometrics (ICB).

[14]  Javier Hernandez-Ortega,et al.  FaceQnet: Quality Assessment for Face Recognition based on Deep Learning , 2019, 2019 International Conference on Biometrics (ICB).

[15]  Dong Cao,et al.  Domain Balancing: Face Recognition on Long-Tailed Domains , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[17]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

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

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

[20]  Mei Wang,et al.  Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

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

[24]  Shengjin Wang,et al.  Linkage Based Face Clustering via Graph Convolution Network , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[26]  Sumohana S. Channappayya,et al.  Blind image quality evaluation using perception based features , 2015, 2015 Twenty First National Conference on Communications (NCC).

[27]  Alan C. Bovik,et al.  No-Reference Image Quality Assessment in the Spatial Domain , 2012, IEEE Transactions on Image Processing.

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

[29]  Xiaogang Wang,et al.  AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Christoph Busch,et al.  Face Image Quality Assessment: A Literature Survey , 2020, ACM Comput. Surv..

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

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

[33]  Dahua Lin,et al.  Learning to Cluster Faces via Confidence and Connectivity Estimation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Anil K. Jain,et al.  IARPA Janus Benchmark-B Face Dataset , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

[36]  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.

[37]  Alan C. Bovik,et al.  Making a “Completely Blind” Image Quality Analyzer , 2013, IEEE Signal Processing Letters.

[38]  Naser Damer,et al.  SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Yichen Wei,et al.  Circle Loss: A Unified Perspective of Pair Similarity Optimization , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[42]  Yichen Wei,et al.  Data Uncertainty Learning in Face Recognition , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  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).

[44]  Julio Gonzalo,et al.  A comparison of extrinsic clustering evaluation metrics based on formal constraints , 2009, Information Retrieval.

[45]  Kihyuk Sohn,et al.  Improved Deep Metric Learning with Multi-class N-pair Loss Objective , 2016, NIPS.

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

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

[48]  Tao Mei,et al.  The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances , 2020, ACM Comput. Surv..

[49]  Anil K. Jain,et al.  Probabilistic Face Embeddings , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).