nach oben

Erschienen in:

2018 | OriginalPaper | Buchkapitel

From Face Recognition to Models of Identity: A Bayesian Approach to Learning About Unknown Identities from Unsupervised Data

verfasst von : Daniel Coelho de Castro, Sebastian Nowozin

Erschienen in: Computer Vision – ECCV 2018

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Current face recognition systems robustly recognize identities across a wide variety of imaging conditions. In these systems recognition is performed via classification into known identities obtained from supervised identity annotations. There are two problems with this current paradigm: (1) current systems are unable to benefit from unlabelled data which may be available in large quantities; and (2) current systems equate successful recognition with labelling a given input image. Humans, on the other hand, regularly perform identification of individuals completely unsupervised, recognising the identity of someone they have seen before even without being able to name that individual. How can we go beyond the current classification paradigm towards a more human understanding of identities? We propose an integrated Bayesian model that coherently reasons about the observed images, identities, partial knowledge about names, and the situational context of each observation. While our model achieves good recognition performance against known identities, it can also discover new identities from unsupervised data and learns to associate identities with different contexts depending on which identities tend to be observed together. In addition, the proposed semi-supervised component is able to handle not only acquaintances, whose names are known, but also unlabelled familiar faces and complete strangers in a unified framework.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel Diverse and Coherent Paragraph Generation from Images

Nur mit Berechtigung zugänglich

See footnote 4.

One could further allow an unbounded number of latent contexts by incorporating a nonparametric context distribution, resulting in a structure akin to the nested DP [5, 23] or the dual DP described in [31]. More details in the online supplement, Sect. A.

One could instead consider a Pitman–Yor process if power-law behaviour seems more appropriate than the DP’s exponential tails [20].

The ‘true’ label likelihood \(F_\mathrm {Y}(\ell \mathbin {|}y^*_i)\) is random due to its dependence on the unobserved prior \(H_\mathrm {Y}\). We thus define \(\widehat{F_\mathrm {Y}}\) as its posterior expectation given the known identity labels \(\mathbf {y}^*\). See supplementary material, Sect. B, for details.

Available at: http://vis-www.cs.umass.edu/lfw/.

The predictive distribution of \(\mathbf {x}_n\) for new identities is a wide Student’s t.

Learned-Miller, E., Huang, G.B., RoyChowdhury, A., Li, H., Hua, G.: Labeled faces in the wild: a survey. In: Kawulok, M., Celebi, M.E., Smolka, B. (eds.) Advances in Face Detection and Facial Image Analysis, pp. 189–248. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-25958-1_8CrossRef

Amos, B., Ludwiczuk, B., Satyanarayanan, M.: OpenFace: A general-purpose face recognition library with mobile applications. Technical report, CMU-CS-16-118, CMU School of Computer Science (2016)

Anguelov, D., Lee, K.C., Gökturk, S.B., Sumengen, B.: Contextual identity recognition in personal photo albums. In: CVPR 2007, pp. 1–7 (2007). https://doi.org/10.1109/CVPR.2007.383057

Betancourt, A., Morerio, P., Regazzoni, C.S., Rauterberg, M.: The evolution of first person vision methods: a survey. IEEE Trans. Circ. Syst. Video Technol. 25(5), 744–760 (2015). https://doi.org/10.1109/TCSVT.2015.2409731CrossRef

Blei, D.M., Griffiths, T.L., Jordan, M.I.: The nested Chinese restaurant process and Bayesian nonparametric inference of topic hierarchies. J. ACM 57(2) (2010). https://doi.org/10.1145/1667053.1667056MathSciNetCrossRef

Bouveyron, C., Girard, S.: Robust supervised classification with mixture models: learning from data with uncertain labels. Pattern Recogn. 42(11), 2649–2658 (2009). https://doi.org/10.1016/j.patcog.2009.03.027CrossRefMATH

Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41(3), 1–58 (2009). https://doi.org/10.1145/1541880.1541882CrossRef

Chapelle, O., Schölkopf, B., Zien, A. (eds.): Semi-supervised Learning. MIT Press, Cambridge (2006)

Choi, J.Y., De Neve, W., Ro, Y.M., Plataniotis, K.: Automatic face annotation in personal photo collections using context-based unsupervised clustering and face information fusion. IEEE Trans. Circ. Syst. Video Technol. 20(10), 1292–1309 (2010). https://doi.org/10.1109/TCSVT.2010.2058470CrossRef

10.

Ferguson, T.S.: A Bayesian analysis of some nonparametric problems. Ann. Stat. 1(2), 209–230 (1973). http://www.jstor.org/stable/2958008MathSciNetCrossRef

11.

Frénay, B., Verleysen, M.: Classification in the presence of label noise: a survey. IEEE Trans. Neural Netw. Learn. Syst. 25(5), 845–869 (2014). https://doi.org/10.1109/TNNLS.2013.2292894CrossRef

12.

Gallagher, A.C., Chen, T.: Using context to recognize people in consumer images. IPSJ Trans. Comput. Vis. Appl. 1, 115–126 (2009). https://doi.org/10.2197/ipsjtcva.1.115CrossRef

13.

Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report, University of Massachusetts Amherst (2007)

14.

Hubert, L., Arabie, P.: Comparing partitions. J. Classif. 2(1), 193–218 (1985). https://doi.org/10.1007/BF01908075CrossRefMATH

15.

Ioffe, S.: Probabilistic linear discriminant analysis. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 531–542. Springer, Heidelberg (2006). https://doi.org/10.1007/11744085_41CrossRef

16.

Jafri, R., Arabnia, H.R.: A survey of face recognition techniques. J. Inf. Process. Syst. 5(2), 41–68 (2009). https://doi.org/10.3745/JIPS.2009.5.2.041CrossRef

17.

Le, N., et al.: Towards large scale multimedia indexing: a case study on person discovery in broadcast news. In: CBMI 2017, pp. 18:1–18:6. ACM (2017). https://doi.org/10.1145/3095713.3095732

18.

Li, P., Fu, Y., Mohammed, U., Elder, J.H., Prince, S.J.D.: Probabilistic models for inference about identity. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 144–157 (2012). https://doi.org/10.1109/TPAMI.2011.104CrossRef

19.

Perdikis, S., Leeb, R., Chavarriaga, R., Millán, J.d.R.: Context-aware learning for finite mixture models (2015). http://arxiv.org/abs/1507.08272

20.

Pitman, J., Yor, M.: The two-parameter Poisson-Dirichlet distribution derived from a stable subordinator. Ann. Probab. 25(2), 855–900 (1997). http://www.jstor.org/stable/2959614MathSciNetCrossRef

21.

Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: Proceedings of the 11th IEEE International Conference on Computer Vision (ICCV 2007). IEEE (2007). https://doi.org/10.1109/ICCV.2007.4409052

22.

Rand, W.M.: Objective criteria for the evaluation of clustering methods. J. Am. Stat. Assoc. 66(336), 846–850 (1971). https://doi.org/10.1080/01621459.1971.10482356CrossRef

23.

Rodríguez, A., Dunson, D.B., Gelfand, A.E.: The nested Dirichlet process. J. Am. Stat. Assoc. 103(483), 1131–1154 (2008). https://doi.org/10.1198/016214508000000553MathSciNetCrossRefMATH

24.

Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Comput. 13(7), 1443–1471 (2001). https://doi.org/10.1162/089976601750264965CrossRefMATH

25.

Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015), pp. 815–823. IEEE, June 2015. https://doi.org/10.1109/CVPR.2015.7298682

26.

Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014), pp. 1701–1708. IEEE, June 2014. https://doi.org/10.1109/CVPR.2014.220

27.

Tapaswi, M., Bäuml, M., Stiefelhagen, R.: “Knock! Knock! Who is it?” Probabilistic person identification in TV-series. In: CVPR 2012, pp. 2658–2665 (2012). https://doi.org/10.1109/CVPR.2012.6247986

28.

Teh, Y.W.: Dirichlet process. In: Sammut, C., Webb, G.I. (eds.) Encyclopedia of Machine Learning, pp. 280–287. Springer, Boston (2010). https://doi.org/10.1007/978-0-387-30164-8_219CrossRef

29.

Teh, Y.W., Jordan, M.I., Beal, M.J., Blei, D.M.: Hierarchical Dirichlet processes. J. Am. Stat. Assoc. 101(476), 1566–1581 (2006). https://doi.org/10.1198/016214506000000302MathSciNetCrossRefMATH

30.

Torralba, A., Murphy, K.P., Freeman, W.T., Rubin, M.A.: Context-based vision system for place and object recognition. In: Proceedings Ninth IEEE International Conference on Computer Vision (ICCV 2003), vol. 1, pp. 273–280 (2003). https://doi.org/10.1109/ICCV.2003.1238354

31.

Wang, X., Ma, X., Grimson, W.E.L.: Unsupervised activity perception in crowded and complicated scenes using hierarchical bayesian models. IEEE Trans. Pattern Anal. Mach. Intell. 31(3), 539–555 (2009). https://doi.org/10.1109/TPAMI.2008.87CrossRef

32.

Zhang, L., Chen, L., Li, M., Zhang, H.: Automated annotation of human faces in family albums. In: MULTIMEDIA 2003, pp. 355–358. ACM Press (2003). https://doi.org/10.1145/957013.957090

33.

Zhao, M., Teo, Y.W., Liu, S., Chua, T.-S., Jain, R.: Automatic person annotation of family photo album. In: Sundaram, H., Naphade, M., Smith, J.R., Rui, Y. (eds.) CIVR 2006. LNCS, vol. 4071, pp. 163–172. Springer, Heidelberg (2006). https://doi.org/10.1007/11788034_17CrossRef

34.

Zhu, X., Ghahramani, Z.: Learning from labeled and unlabeled data with label propagation. Technical report, CMU-CALD-02-107, Carnegie Mellon University (2002)

Titel: From Face Recognition to Models of Identity: A Bayesian Approach to Learning About Unknown Identities from Unsupervised Data
verfasst von: Daniel Coelho de Castro
Sebastian Nowozin
Verlag: Springer International Publishing
Buch: Computer Vision – ECCV 2018
Print ISBN: 978-3-030-01215-1

Electronic ISBN: 978-3-030-01216-8

Copyright-Jahr: 2018
DOI: https://doi.org/10.1007/978-3-030-01216-8_46

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"