Abstract
Face verification (FV) is a challenging problem, because occlusion, posture, illumination, aging will affect the accuracy of FV. Deep convolutional neural networks (DCNNs) have been widely used in many computer vision tasks. Due to the strong feature learning ability, DCNNs improve the accuracy of FV while they also bring some problems such as overfitting. Erasing has been proven to be an effective method for reducing overfitting, while the erasing position is seldom considered. We analyse the effect of different erasing positions and propose a novel data augmentation method especially for FV, called Fixed Erasing(FE). We randomly erase some face images with random size of rectangles centered on fixed facial landmarks such as the centers of eyes, tip of noses and the corners of mouths. Our method can alleviate the risk of overfitting and make the models learn more robust features. And our method can be easily merged with most DCNN-based FV models through a few lines of code. Extensive experiments demonstrate that FE can improve the performance of most recently proposed FV models on several popular benchmarks.
Similar content being viewed by others
References
Cao Q, Li S, Xie W, Parkhi OM, Zisserman A (2017) Vggface2: a dataset for recognising faces across pose and age. CoRR, arXiv:1710.08092
Chen B, Deng W, Du J (2017) Noisy softmax: improving the generalization ability of DCNN via postponing the early softmax saturation. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp 4021–4030
Chen S, Liu Y, Gao X, Han Z (2018) Mobilefacenets: efficient cnns for accurate real-time face verification on mobile devices. CoRR, arXiv:1804.07573
Deng J, Guo J, Zafeiriou S (2018) Arcface: additive angular margin loss for deep face recognition CoRR, arXiv:1801.07698
Deng W, Hu J, Zhang N, Chen B, Guo J (2017) Fine-grained face verification: Fglfw database, baselines, and human-dcmn partnership. Pattern Recogn 66:63–73
Ding C, Tao D (2018) Trunk-branch ensemble convolutional neural networks for video-based face recognition. IEEE Trans Pattern Anal Mach Intell 40(4):1002–1014
Dong X, Yan Y, Tan M, Yi Y, Tsang IW (2018) Late fusion via subspace search with consistency preservation. IEEE Trans Image Process PP(99):1–1
Guo Y, Zhang L, Hu Y, He X, Gao J (2016) Ms-celeb-1m: a dataset and benchmark for large-scale face recognition. In: Computer Vision - ECCV 2016 - 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III, pp 87–102
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR Las Vegas, NV, USA, June 27-30, 2016. IEEE Computer Society, p 2016
Huang GB, Ramesh M, Berg T, Learned-Miller E (2007) Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical Report 07-49. University of Massachusetts, Amherst
Huang R, Zhang S, Li T, He R (2017) Beyond face rotation: global and local perception GAN for photorealistic and identity preserving frontal view synthesis. In: IEEE international conference on computer vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp 2458–2467
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach FR, Blei DM (eds) Proceedings of the 32nd international conference on machine learning, ICML 2015, Lille, France, 6-11 July 2015, vol 37 of JMLR workshop and conference proceedings, pp 448–456, JMLR.org
Jan A, Ding H, Meng H, Chen L, Li H (2018) Accurate facial parts localization and deep learning for 3d facial expression recognition. CoRR, arXiv:1803.05846
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Bartlett PL, Pereira FCN, Burges CJC, Bottou L, Weinberger KQ (eds) Advances in neural information processing systems 25: 26th annual conference on neural information processing systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States, pp 1106–1114
Liu J, Deng Y, Bai T, Huang C (2015) Targeting ultimate accuracy: face recognition via deep embedding. CoRR, arXiv:1506.07310
Liu W, Wen Y, Yu Z, Li M, Raj B, Song L (2017) Sphereface: deep hypersphere embedding for face recognition. In: 2017 IEEE conference on computer vision and pattern recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017. IEEE Computer Society, pp 6738–6746
Liu Y, Zhang L, Nie L, Yan Y, Rosenblum DS (2016) Fortune teller: predicting your career path. In: Proceedings of the thirtieth AAAI conference on artificial intelligence, February 12-17, 2016, Phoenix, Arizona, USA, pp 201–207
Liu Y, Zheng Y, Liang Y, Liu S, Rosenblum DS (2016) Urban water quality prediction based on multi-task multi-view learning. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence, IJCAI 2016, New York, NY, USA, 9-15 July 2016, pp 2576–2581
Liu Y, Li H, Wang X (2017) Rethinking feature discrimination and polymerization for large-scale recognition. CoRR, arXiv:1710.00870
Liu Y, Li H, Yan J, Wei F, Wang X, Tang X (2017) Recurrent scale approximation for object detection in CNN. In: IEEE International Conference on Computer Vision, ICCV 2017 Venice, Italy, October 22-29, 2017, pp 571–579
Nguyen HV, Bai L (2010) Cosine similarity metric learning for face verification. In: Computer vision - ACCV 2010 - 10th Asian conference on computer vision, Queenstown, New Zealand, November 8-12 2010, Revised selected papers, Part II, pp 709–720
Ranjan R, Castillo CD, Chellappa R (2017) L2-constrained softmax loss for discriminative face verification. CoRR, arXiv:1703.09507
Salimans T, Kingma DP (2016) Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: Lee DD, Sugiyama M, von Luxburg U, Guyon I, Garnett R (eds) Advances in neural information processing systems 29: annual conference on neural information processing systems 2016, December 5-10, 2016, Barcelona, Spain, p 901
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR, arXiv:1409.1556
Sun Y, Wang X, Tang X (2014) Deep learning face representation by joint identification-verification. Adv Neural Inf Proces Syst 27:1988–1996
Sun Y, Wang X, Tang X (2014) Deep learning face representation from predicting 10,000 classes. In: Annual conference on neural information processing systems 2014. IEEE Computer Society, pp 1891–1898
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Singh SP, Markovitch S (eds) Proceedings of the thirty-first AAAI conference on artificial intelligence, February 4-9 San Francisco, California, USA. AAAI Press, p 2017
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR Las Vegas, NV, USA, June 27-30, 2016. IEEE Computer Society, p 2016
Taigman Y, Yang M, Ranzato M’A, Wolf L (2014) Deepface: closing the gap to human-level performance in face verification. In: 2014 IEEE conference on computer vision and pattern recognition, CVPR 2014, Columbus, OH, USA, June 23-28, 2014, pp 1701–1708
Wan L, Zeiler MD, Zhang S, LeCun Y, Fergus R (2013) Regularization of neural networks using dropconnect. In: Proceedings of the 30th international conference on machine learning, ICML 2013, Atlanta, GA, USA, 16-21 June 2013, vol 28 of JMLR workshop and conference proceedings, pp 1058–1066, JMLR.org
Wang F, Liu W, Liu H, Cheng J (2018) Additive margin softmax for face verification. CoRR, arXiv:1801.05599
Wang F, Xiang X, Cheng J, Yuille AL (2017) Normface: L2 hypersphere embedding for face verification. In: Proceedings of the 2017 ACM on multimedia conference, MM 2017, Mountain View, CA, USA, October 23-27, 2017, pp 1041–1049
Wang X, Shrivastava A, Gupta A (2017) A-fast-rcnn: hard positive generation via adversary for object detection. In: Conference on Computer Vision and Pattern Recognition (CVPR)
Wen Y, Zhang K, Li Z, Qiao Y (2016) A discriminative feature learning approach for deep face recognition. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision - ECCV 2016 - 14th European conference, Amsterdam, The Netherlands, October 11-14, 2016 Proceedings, Part VII, vol 9911 of Lecture notes in computer science. Springer, pp 499–515
Wu Y, He K (2018) Group normalization. CoRR, arXiv:1803.08494
Xie L, Wang J, Wei Z, Wang M, Tian Q (2016) Disturblabel: regularizing CNN on the loss layer. In: 2016 IEEE conference on computer vision and pattern recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp 4753–4762
Ye L, Nie L, Lei H, Zhang L, Rosenblum DS (2016) Action2activity: recognizing complex activities from sensor data
Ye L, Nie L, Li L, Rosenblum D (2016) From action to activity: sensor-based activity recognition. Neurocomputing 181:108–115
Yi D, Lei Z, Liao S, Li SZ (2014) Learning face representation from scratch. CoRR, arXiv:1411.7923
Yu J, Rui Y, Tang YY, Tao D (2014) High-order distance-based multiview stochastic learning in image classification. IEEE Trans Cybernetics 44(12):2431–2442
Yu J, Tao D, Li J, Cheng J (2014) Semantic preserving distance metric learning and applications. Inf Sci 281:674–686
Yuan C, Guo J, Feng P, Zhao Z, Xu C, Wang T, Choe G, Duan K (2019) A jointly learned deep embedding for person re-identification. Neurocomputing 330:127–137
Zeiler MD, Fergus R (2013) Stochastic pooling for regularization of deep convolutional neural networks. CoRR, arXiv:1301.3557
Zhang K, Zhang Z, Li Z, Yu Q (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23(10):1499–1503
Zhang S, Zhu X, Lei Z, Shi H, Wang X, Li SZ (2017) Faceboxes: a CPU real-time face detector with high accuracy. In: 2017 IEEE international joint conference on biometrics, IJCB 2017, Denver, CO, USA, October 1-4, 2017, pp 1–9
Zhong Z, Zheng L, Kang G, Li S, Yi Y (2017) Random erasing data augmentation. CoRR, arXiv:1708.04896
Acknowledgements
This work was supported in part by the Natural Science Foundation of China under Grant U1536203, in part by the National key research and development program of China(2016QY01W0200), in part by the Major Scientific and Technological Project of Hubei Province (2018AAA068).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lei, J., Zhang, B. & Ling, H. Deep learning face representation by fixed erasing in facial landmarks. Multimed Tools Appl 78, 27703–27718 (2019). https://doi.org/10.1007/s11042-019-07892-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-07892-8