Abstract
Metric learning has been widely used in face and kinship verification and a number of such algorithms have been proposed over the past decade. However, most existing metric learning methods only learn one Mahalanobis distance metric from a single feature representation for each face image and cannot deal with multiple feature representations directly. In many face verification applications, we have access to extract multiple features for each face image to extract more complementary information, and it is desirable to learn distance metrics from these multiple features so that more discriminative information can be exploited than those learned from individual features. To achieve this, we propose a new large margin multi-metric learning (LM\(^3\)L) method for face and kinship verification in the wild. Our method jointly learns multiple distance metrics under which the correlations of different feature representations of each sample are maximized, and the distance of each positive is less than a low threshold and that of each negative pair is greater than a high threshold, simultaneously. Experimental results show that our method can achieve competitive results compared with the state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Available: http://www.openu.ac.il/home/hassner/data/lfwa/.
- 2.
Available: http://vis-www.cs.umass.edu/lfw/results.html.
References
Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: application to face recognition. TPAMI 28, 2037–2041 (2006)
Barkan, O., Weill, J., Wolf, L., Aronowitz, H.: Fast high dimensional vector multiplication face recognition. In: ICCV, pp. 1960–1967 (2013)
Cao, Q., Ying, Y., Li, P.: Similarity metric learning for face recognition. In: ICCV, pp. 2408–2415 (2013)
Cao, Z., Yin, Q., Tang, X., Sun, J.: Face recognition with learning-based descriptor. In: CVPR, pp. 2707–2714 (2010)
Cui, Z., Li, W., Xu, D., Shan, S., Chen, X.: Fusing robust face region descriptors via multiple metric learning for face recognition in the wild. In: CVPR, pp. 3554–3561 (2013)
Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML, pp. 209–216 (2007)
Fang, R., Tang, K., Snavely, N., Chen, T.: Towards computational models of kinship verification. In: ICIP, pp. 1577–1580 (2010)
Goldberger, J., Roweis, S.T., Hinton, G.E., Salakhutdinov, R.: Neighbourhood components analysis. In: NIPS, pp. 513–520 (2004)
Guillaumin, M., Verbeek, J.J., Schmid, C.: Is that you? metric learning approaches for face identification. In: ICCV, pp. 498–505 (2009)
Guo, G., Wang, X.: Kinship measurement on salient facial features. TIM 61, 2322–2325 (2012)
Hu, J., Lu, J., Tan, Y.P.: Discriminative deep metric learning for face verification in the wild. In: CVPR, pp. 1875–1882 (2014)
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 07–49, University of Massachusetts, Amherst (2007)
Köstinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: CVPR, pp. 2288–2295 (2012)
Lei, Z., Pietikainen, M., Li, S.Z.: Learning discriminant face descriptor. TPAMI 36, 289–302 (2014)
Li, H., Hua, G., Lin, Z., Brandt, J., Yang, J.: Probabilistic elastic matching for pose variant face verification. In: CVPR, pp. 3499–3506 (2013)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Lu, J., Hu, J., Zhou, X., Shang, Y., Tan, Y.P., Wang, G.: Neighborhood repulsed metric learning for kinship verification. In: CVPR, pp. 2594–2601 (2012)
Lu, J., Zhou, X., Tan, Y.P., Shang, Y., Zhou, J.: Neighborhood repulsed metric learning for kinship verification. TPAMI 36, 331–345 (2014)
Mendez-Vazquez, H., Martinez-Diaz, Y., Chai, Z.: Volume structured ordinal features with background similarity measure for video face recognition. In: ICB, pp. 1–6 (2013)
Mignon, A., Jurie, F.: Pcca: A new approach for distance learning from sparse pairwise constraints. In: CVPR, pp. 2666–2672 (2012)
Nguyen, H.V., Bai, L.: Cosine similarity metric learning for face verification. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part II. LNCS, vol. 6493, pp. 709–720. Springer, Heidelberg (2011)
Rennie, J.D.M., Srebro, N.: Fast maximum margin matrix factorization for collaborative prediction. In: ICML, pp. 713–719 (2005)
Seo, H.J., Milanfar, P.: Face verification using the lark representation. TIFS 6, 1275–1286 (2011)
Sharma, A., Kumar, A., Daume III, H., Jacobs, D.: Generalized multiview analysis: a discriminative latent space. In: CVPR, pp. 1867–1875 (2012)
Simonyan, K., Parkhi, O.M., Vedaldi, A., Zisserman, A.: Fisher vector faces in the wild. In: BMVC, pp. 1–12 (2013)
Torresani, L., Lee, K.C.: Large margin component analysis. In: NIPS, pp. 1385–1392 (2006)
Tran, D., Sorokin, A.: Human activity recognition with metric learning. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 548–561. Springer, Heidelberg (2008)
Wang, Z., Hu, Y., Chia, L.-T.: Image-to-class distance metric learning for image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 706–719. Springer, Heidelberg (2010)
Weinberger, K.Q., Blitzer, J., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. In: NIPS (2005)
Wolf, L., Hassner, T., Maoz, I.: Face recognition in unconstrained videos with matched background similarity. In: CVPR, pp. 529–534 (2011)
Wolf, L., Hassner, T., Taigman, Y.: Descriptor based methods in the wild. In: ECCVW (2008)
Wolf, L., Levy, N.: The svm-minus similarity score for video face recognition. In: CVPR, pp. 3523–3530 (2013)
Xia, S., Shao, M., Fu, Y.: Kinship verification through transfer learning. In: IJCAI, pp. 2539–2544 (2011)
Xia, S., Shao, M., Luo, J., Fu, Y.: Understanding kin relationships in a photo. TMM 14, 1046–1056 (2012)
Yi, D., Lei, Z., Li, S.Z.: Towards pose robust face recognition. In: CVPR, pp. 3539–3545 (2013)
Ying, Y., Li, P.: Distance metric learning with eigenvalue optimization. JMLR 13, 1–26 (2012)
Zhou, X., Hu, J., Lu, J., Shang, Y., Guan, Y.: Kinship verification from facial images under uncontrolled conditions. In: ACM MM, pp. 953–956 (2011)
Zhou, X., Lu, J., Hu, J., Shang, Y.: Gabor-based gradient orientation pyramid for kinship verification under uncontrolled environments. In: ACM MM, pp. 725–728 (2012)
Acknowledgement
This work was carried out at the Rapid-Rich Object Search (ROSE) Lab at the Nanyang Technological University, Singapore. The ROSE Lab is supported by a grant from the Singapore National Research Foundation. This grant is administered by the Interactive & Digital Media Programme Office at the Media Development Authority, Singapore.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Hu, J., Lu, J., Yuan, J., Tan, YP. (2015). Large Margin Multi-metric Learning for Face and Kinship Verification in the Wild. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9005. Springer, Cham. https://doi.org/10.1007/978-3-319-16811-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-16811-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16810-4
Online ISBN: 978-3-319-16811-1
eBook Packages: Computer ScienceComputer Science (R0)