Improve Cross-Domain Face Recognition with IBN-block

Domain adaptation is one of the major challenges for face recognition (FR). Most large-scale FR training datasets are built from massive images crawled from the Internet, while in practical applications face images come from specific scenarios. Especially, for applications like ID card verification, registered face images are taken in controlled environments while probe face images are not. There are different distributions between source domain and target domain. In this paper, we propose to use Instance-Batch-Normalization (IBN) block to improve cross-domain FR performance. A million-scale cross-domain test set named IDCard-Scene-1M is used for evaluation. CNN models are trained with an improved loss function which we call L2-ASoftmax Loss. Without using any data from the target domain, IBN-block increased recall rates (@FPR = 10−6) on IDCard-Scene-1M by 1 percentage point for different CNN models. Besides, experiments show that the proposed IBN-CNN models trained with L2-ASoftmax Loss made state-of-the-art performance on MegaFace evaluation.

[1]  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).

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

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

[5]  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).

[6]  Xiaoou Tang,et al.  Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net , 2018, ECCV.

[7]  Nir Ailon,et al.  Deep Metric Learning Using Triplet Network , 2014, SIMBAD.

[8]  Jian Sun,et al.  Bayesian Face Revisited: A Joint Formulation , 2012, ECCV.

[9]  Andrea Vedaldi,et al.  Improved Texture Networks: Maximizing Quality and Diversity in Feed-Forward Stylization and Texture Synthesis , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[12]  Andrea Lagorio,et al.  On the Use of SIFT Features for Face Authentication , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

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

[14]  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).

[15]  Trevor Darrell,et al.  Deep Domain Confusion: Maximizing for Domain Invariance , 2014, CVPR 2014.

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

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

[18]  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.

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

[20]  Mahadev Satyanarayanan,et al.  OpenFace: A general-purpose face recognition library with mobile applications , 2016 .

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

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

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

[24]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

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

[26]  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).

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

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

[29]  Joni-Kristian Kämäräinen,et al.  Simple Gabor feature space for invariant object recognition , 2004, Pattern Recognit. Lett..

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

[31]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

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

[33]  Timothy F. Cootes,et al.  Toward Automatic Simulation of Aging Effects on Face Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  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).

[35]  Swami Sankaranarayanan,et al.  Unsupervised Domain Adaptation for Semantic Segmentation with GANs , 2017, ArXiv.

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