第5期 夏洋洋,等:人脸识别背后的数据清理问题研究 .623· verification[J].IEEE transactions on pattern analysis and [22]GUO Y,ZHANG L,HU Y,et al.MS-celeb-1M:a dataset machine intelligence,2016,38(10):1997-2009. and benchmark for large-scale face recognition[C]//IEEE [9]TAIGMAN Y,YANG M,RANZATO M,et al.Deepface: Conference on Computer Vision and Pattern Recognition. closing the gap to human-level performance in face Las Vegas,USA,2016:113-124. verification[C]//IEEE Conference on Computer Vision and [23]BANSAL A,NANDURI A,CASTILLO C,et al.UMDFaces: Pattern Recognition.Columbia,American, 2014: an annotated face dataset for training deep networks[C]/ 1701-1708. IEEE Conference on Computer Vision and Pattern [10]WEN Y,ZHANG K,LI Z,et al.A discriminative feature Recognition.Las Vegas,USA,2016:976-984. learning approach for deep face recognition C]//ECCV [24]WOLF L,HASSENER T,MAOZ I.Face recognition in Conference on Computer Vision.Amsterdam,Holand, unconstrained videos with matched background similarity 2016:499-515. [C]//Computer Vision and Pattern Recognition.Colorado [11]HUANG G B,MATTAR M,BERG T,et al.Labeled faces Springs,USA,2011:529-534. in the wild:a database for studying face recognition in [25 GUO Y,ZHANG L.One-shot face recognition by unconstrained environments[J].Month,2007. promoting underrepresented classes[].Computer vision [12 SUN Y,WANG X,TANG X.Deep learning face and pattern recognition,arxiv:1707.05574,2017. representation from predicting 10,000 classes[C]//IEEE [26]NECH A,Kemelmachershlizerman I.Level playing field Conference on Computer Vision and Pattern Recognition. for million scale face recognition[.Computer vision and Hawaii,USA,2014:1891-1898. pattern recognition,arxiv:1705.00393,2017. [13]LIU J,DENG Y,BAI T,et al.Targeting ultimate [27]ZHANG K,ZHANG Z,LI Z,et al.Joint face detection and accuracy:face recognition via deep embedding [C]/ alignment using multitask cascaded convolutional networks[J] European Conference on Computer Vision.Amsterdam, IEEE signal processing letters,2016,23(10):1499-1503. Netherlands,2016:499-515. [28]HUANG G.B,LEARNED-MILLER E.Labeled faces in the [14]TAIGMAN Y.YANG M,RANZATO M,et al.Web-scale wild:updates and new reporting procedures[R].Technical training for face identification[C]//Computer Vision and report UM-CS-2014-003. Pattern Recognition.Columbus,USA,2014:2746-2754. [29]JIA Y,SHELHAMER E,DONAHUE J,et al.Caffe: [15 SUN Y,WANG X,TANG X.Deeply learned face convolutional architecture for fast feature embedding [J]. representations are sparse,selective,and robust[C]// Eprint arxiv,2014:675-678. Computer Vision and Pattern Recognition.Boston,USA, [30]LIU F,ZENG D,ZHAO Q,et al.Joint face alignment and 2015:2892-2900. 3D face reconstruction C]//European Conference on [16]SCHROFF F,KALENICHENKO D,PHILBIN J.Facenet: Computer Vision.Amsterdam,Netherlands,2016:545-560. a unified embedding for face recognition and clustering 作者简介: [C]//IEEE Conference on Computer Vision and Pattern 夏洋洋,男,1990年生,硕士研究 Recognition.Boston,USA,2015:815-823. 生,主要研究方向为深度学习、图像处 [17]WEN Y,ZHANG K,LI Z,et al.A discriminative feature 理、人脸识别。 learning approach for deep face recognition[C]//European Conference on Computer Vision.Amsterdam,Netherlands, 2016:499-515. [18]SEITZ S M,MILLER D,et al.The megaface benchmark: 1 million faces for recognition at scale[C]//Computer 龚勋,男,1980年生,副教授,博士, Vision and Pattern Recognition.Las Vegas,USA,2016: 主要研究方向为图像处理及模式识别、 4873-4882 三维人脸建模、人脸图像分析及识别。 [19]BORJI A,IZADI S,ITTI L.iLab-20M:a large-scale 获国家发明专利2项,发表学术论文30 controlled object dataset to investigate deep learning[Cl// 余篇,出版专著1部。 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,USA,2016:2221-2230. [20]KEMELMACHERSHLIZERMAN I.SEITZ S M.MILLER D,et al.The megaface benchmark:I million faces for 洪西进,男,1957年生,特聘教授 recognition at scale C]//Computer Vision and Pattern 博士,主要研究方向为信息安全、生物 Recognition.Las Vegas,USA,2016:4873-4882. 辨识、云计算与大数据、智能图像处理。 [21]GUO Y,ZHANG L,HU Y,et al.MS-Celeb-1M:challenge 发明专利13项,发表SC期刊学术论 of recognizing one million celebrities in the real world[C/ 文80余篇,国际学术会议论文110 Electronic imaging.San Francisco,USA,2016:1-6. 余篇。verification[ J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 38(10): 1997-2009. [9] TAIGMAN Y, YANG M, RANZATO M, et al. Deepface: closing the gap to human⁃level performance in face verification[C] / / IEEE Conference on Computer Vision and Pattern Recognition. Columbia, American, 2014: 1701-1708. [10]WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition [ C] / / ECCV Conference on Computer Vision. Amsterdam, Holand, 2016: 499-515. [11]HUANG G B,MATTAR M, BERG T, et al. Labeled faces in the wild: a database for studying face recognition in unconstrained environments[J].Month, 2007. [ 12 ] SUN Y, WANG X, TANG X. Deep learning face representation from predicting 10,000 classes[C] / / IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA, 2014: 1891-1898. [ 13 ] LIU J, DENG Y, BAI T, et al. Targeting ultimate accuracy: face recognition via deep embedding [ C ] / / European Conference on Computer Vision. Amsterdam, Netherlands, 2016: 499-515. [14]TAIGMAN Y, YANG M, RANZATO M, et al. Web⁃scale training for face identification[C] / / Computer Vision and Pattern Recognition.Columbus, USA, 2014: 2746-2754. [15 ] SUN Y, WANG X, TANG X. Deeply learned face representations are sparse, selective, and robust [ C] / / Computer Vision and Pattern Recognition. Boston, USA, 2015: 2892-2900. [16]SCHROFF F, KALENICHENKO D, PHILBIN J. Facenet: a unified embedding for face recognition and clustering [C] / / IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA, 2015: 815-823. [17]WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition[C] / / European Conference on Computer Vision. Amsterdam, Netherlands, 2016: 499-515. [18]SEITZ S M, MILLER D, et al.The megaface benchmark: 1 million faces for recognition at scale [ C] / / Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 4873-4882. [ 19] BORJI A, IZADI S, ITTI L. iLab⁃20M: a large⁃scale controlled object dataset to investigate deep learning[C] / / IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 2221-2230. [20]KEMELMACHERSHLIZERMAN I, SEITZ S M, MILLER D, et al. The megaface benchmark: 1 million faces for recognition at scale [ C] / / Computer Vision and Pattern Recognition. Las Vegas, USA, 2016:4873-4882. [21]GUO Y, ZHANG L, HU Y, et al. MS⁃Celeb⁃1M: challenge of recognizing one million celebrities in the real world[C] / / Electronic imaging. San Francisco,USA,2016: 1-6. [22]GUO Y, ZHANG L, HU Y, et al. MS⁃celeb⁃1M: a dataset and benchmark for large⁃scale face recognition[C] / / IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 113-124. [23]BANSAL A, NANDURI A, CASTILLO C, et al. UMDFaces: an annotated face dataset for training deep networks[C] / / IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 976-984. [24] WOLF L, HASSENER T, MAOZ I. Face recognition in unconstrained videos with matched background similarity [C] / / Computer Vision and Pattern Recognition. Colorado Springs, USA, 2011:529-534. [ 25 ] GUO Y, ZHANG L. One⁃shot face recognition by promoting underrepresented classes [ J]. Computer vision and pattern recognition, arxiv:1707.05574,2017. [26] NECH A, Kemelmachershlizerman I. Level playing field for million scale face recognition[ J]. Computer vision and pattern recognition, arxiv:1705.00393,2017. [27] ZHANG K, ZHANG Z, LI Z, et al. Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE signal processing letters, 2016, 23(10):1499-1503. [ 28]HUANG G.B, LEARNED⁃MILLER E. Labeled faces in the wild: updates and new reporting procedures[R]. Technical report UM⁃CS⁃2014-003. [29] JIA Y, SHELHAMER E, DONAHUE J, et al. Caffe: convolutional architecture for fast feature embedding [ J]. Eprint arxiv, 2014:675-678. [ 30]LIU F, ZENG D, ZHAO Q, et al. Joint face alignment and 3D face reconstruction [ C ] / / European Conference on Computer Vision. Amsterdam,Netherlands, 2016: 545-560. 作者简介: 夏洋洋,男, 1990 年生,硕士研究 生,主要研究方向为深度学习、图像处 理、人脸识别。 龚勋,男,1980 年生,副教授,博士, 主要研究方向为图像处理及模式识别、 三维人脸建模、人脸图像分析及识别。 获国家发明专利 2 项,发表学术论文 30 余篇,出版专著 1 部。 洪西进,男,1957 年生,特聘教授, 博士,主要研究方向为信息安全、生物 辨识、云计算与大数据、智能图像处理。 发明专利 13 项,发表 SCI 期刊学术论 文 80 余 篇, 国 际 学 术 会 议 论 文 110 余篇。 第 5 期 夏洋洋,等:人脸识别背后的数据清理问题研究 ·623·