Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition

Face recognition has witnessed great progress in recent years, mainly attributed to the high-capacity model designed and the abundant labeled data collected. However, it becomes more and more prohibitive to scale up the current million-level identity annotations. In this work, we show that unlabeled face data can be as effective as the labeled ones. Here, we consider a setting closely mimicking the real-world scenario, where the unlabeled data are collected from unconstrained environments and their identities are exclusive from the labeled ones. Our main insight is that although the class information is not available, we can still faithfully approximate these semantic relationships by constructing a relational graph in a bottom-up manner. We propose Consensus-Driven Propagation (CDP) to tackle this challenging problem with two modules, the “committee” and the “mediator”, which select positive face pairs robustly by carefully aggregating multi-view information. Extensive experiments validate the effectiveness of both modules to discard outliers and mine hard positives. With CDP, we achieve a compelling accuracy of 78.18% on MegaFace identification challenge by using only 9% of the labels, comparing to 61.78% when no unlabeled data are used and 78.52% when all labels are employed.

[1]  Ronald Rosenfeld,et al.  Semi-supervised learning with graphs , 2005 .

[2]  Xiaoou Tang,et al.  Mix-and-Match Tuning for Self-Supervised Semantic Segmentation , 2017, AAAI.

[3]  Gian Luca Marcialis,et al.  Semi-supervised PCA-Based Face Recognition Using Self-training , 2006, SSPR/SPR.

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

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

[6]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[7]  O. Chapelle,et al.  Semi-Supervised Learning (Chapelle, O. et al., Eds.; 2006) [Book reviews] , 2009, IEEE Transactions on Neural Networks.

[8]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

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

[10]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[12]  Shlomo Argamon,et al.  Committee-Based Sample Selection for Probabilistic Classifiers , 1999, J. Artif. Intell. Res..

[13]  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).

[14]  Martial Hebert,et al.  Semi-Supervised Self-Training of Object Detection Models , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.

[15]  David Yarowsky,et al.  Unsupervised Word Sense Disambiguation Rivaling Supervised Methods , 1995, ACL.

[16]  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).

[17]  Xuran Zhao,et al.  Semi-supervised face recognition with LDA self-training , 2011, 2011 18th IEEE International Conference on Image Processing.

[18]  Ming-Hsuan Yang,et al.  Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  H. Sebastian Seung,et al.  Query by committee , 1992, COLT '92.

[20]  Forrest N. Iandola,et al.  DenseNet: Implementing Efficient ConvNet Descriptor Pyramids , 2014, ArXiv.

[21]  Cheng Li,et al.  Pose-Robust Face Recognition via Deep Residual Equivariant Mapping , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[22]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[24]  Alan L. Yuille,et al.  Semi-Supervised Sparse Representation Based Classification for Face Recognition With Insufficient Labeled Samples , 2016, IEEE Transactions on Image Processing.

[25]  Lei Yang,et al.  Accelerated Training for Massive Classification via Dynamic Class Selection , 2018, AAAI.

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

[27]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[28]  Tom Michael Mitchell,et al.  The Role of Unlabeled Data in Supervised Learning , 2004 .

[29]  Stefan Winkler,et al.  A data-driven approach to cleaning large face datasets , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[30]  Virginia R. de Sa,et al.  Learning Classification with Unlabeled Data , 1993, NIPS.

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

[32]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[33]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

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

[35]  Shaogang Gong,et al.  Stream-based joint exploration-exploitation active learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[36]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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