Curriculum Learning for Face Recognition

We present a novel curriculum learning (CL) algorithm for face recognition using convolutional neural networks. Curriculum learning is inspired by the fact that humans learn better, when the presented information is organized in a way that covers the easy concepts first, followed by more complex ones. It has been shown in the literature that that CL is also beneficial for machine learning tasks by enabling convergence to a better local minimum. In the proposed CL algorithm for face recognition, we divide the training set of face images into subsets of increasing difficulty based on the head pose angle obtained from the absolute sum of yaw, pitch and roll angles. These subsets are introduced to the deep CNN in order of increasing difficulty. Experimental results on the large-scale CASIA-WebFace-Sub dataset show that the increase in face recognition accuracy is statistically significant when CL is used, as compared to organizing the training data in random batches.

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

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

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

[4]  Hongtao Lu,et al.  A new representation method of head images for head pose estimation , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[5]  Daphna Weinshall,et al.  On The Power of Curriculum Learning in Training Deep Networks , 2019, ICML.

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

[7]  Javier R. Movellan,et al.  Generalized adaptive view-based appearance model: Integrated framework for monocular head pose estimation , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[8]  Samy Bengio,et al.  Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks , 2015, NIPS.

[9]  Norbert Krüger,et al.  Face recognition by elastic bunch graph matching , 1997, Proceedings of International Conference on Image Processing.

[10]  Carlos D. Castillo,et al.  UMDFaces: An annotated face dataset for training deep networks , 2016, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[11]  Louis-Philippe Morency,et al.  OpenFace 2.0: Facial Behavior Analysis Toolkit , 2018, 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018).

[12]  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).

[13]  Christoph H. Lampert,et al.  Curriculum learning of multiple tasks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  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.

[15]  Yaser Sheikh,et al.  OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[17]  L. Spreeuwers,et al.  The impact of image quality on the performance of face recognition , 2012 .

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

[19]  Louis-Philippe Morency,et al.  Curriculum Learning for Facial Expression Recognition , 2017, 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017).

[20]  J. Elman.  Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[21]  Lei Zhang,et al.  Active Self-Paced Learning for Cost-Effective and Progressive Face Identification , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Chen Huang,et al.  Deep Imbalanced Learning for Face Recognition and Attribute Prediction , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Nicu Sebe,et al.  Best of Automatic Face and Gesture Recognition 2008 , 2010, Image Vis. Comput..

[24]  Andrea F. Abate,et al.  2D and 3D face recognition: A survey , 2007, Pattern Recognit. Lett..

[25]  Takeo Kanade,et al.  Computer recognition of human faces , 1980 .

[26]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[27]  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).

[28]  M. Kubát.  An Introduction to Machine Learning , 2017, Springer International Publishing.

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

[30]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

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

[32]  Luc Van Gool,et al.  Real time head pose estimation with random regression forests , 2011, CVPR 2011.

[33]  Vanya Avramova.  Curriculum Learning with Deep Convolutional Neural Networks , 2015 .

[34]  Peter Robinson,et al.  OpenFace: An open source facial behavior analysis toolkit , 2016, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[35]  Takeo Kanade,et al.  Multi-PIE , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[36]  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).