Shrinkage Expansion Adaptive Metric Learning

  • Qilong Wang
  • Wangmeng Zuo
  • Lei Zhang
  • Peihua Li
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8695)


Conventional pairwise constrained metric learning methods usually restrict the distance between samples of a similar pair to be lower than a fixed upper bound, and the distance between samples of a dissimilar pair higher than a fixed lower bound. Such fixed bound based constraints, however, may not work well when the intra- and inter-class variations are complex. In this paper, we propose a shrinkage expansion adaptive metric learning (SEAML) method by defining a novel shrinkage-expansion rule for adaptive pairwise constraints. SEAML is very effective in learning metrics from data with complex distributions. Meanwhile, it also suggests a new rule to assess the similarity between a pair of samples based on whether their distance is shrunk or expanded after metric learning. Our extensive experimental results demonstrated that SEAML achieves better performance than state-of-the-art metric learning methods. In addition, the proposed shrinkage-expansion adaptive pairwise constraints can be readily applied to many other pairwise constrained metric learning algorithms, and boost significantly their performance in applications such as face verification on LFW and PubFig databases.


Shrinkage-expansion rule adaptive bound constraints pairwise constrained metric learning face verification 

Supplementary material

978-3-319-10584-0_30_MOESM1_ESM.pdf (44 kb)
Electronic Supplementary Material (PDF 44 KB)


  1. 1.
    Arashloo, S.R., Kittler, J.: Efficient processing of MRFs for unconstrained-pose face recognition. In: BTAS (2013)Google Scholar
  2. 2.
    Asuncion, A., Newman, D.: UCI machine learning repository (2007),
  3. 3.
    Bellet, A., Habrard, A., Sebban, M.: A survey on metric learning for feature vectors and structured data. arXiv 1306.6709 (2013)Google Scholar
  4. 4.
    Chang, C.C., Lin, C.J.: Libsvm: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011)CrossRefGoogle Scholar
  5. 5.
    Csiszár, I., Tusnády, G.: Information geometry and alternating minimization procedures. Statistics and Decisions (1984)Google Scholar
  6. 6.
    Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML (2007)Google Scholar
  7. 7.
    Feng, Z., Jin, R., Jain, A.: Large-scale image annotation by efficient and robust kernel metric learning. In: ICCV (2013)Google Scholar
  8. 8.
    Globerson, A., Roweis, S.: Metric learning by collapsing classes. In: NIPS (2005)Google Scholar
  9. 9.
    Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood components analysis. In: NIPS (2004)Google Scholar
  10. 10.
    Guillaumin, M., Verbeek, J., Schmid, C.: Is that you? metric learning approaches for face identification. In: ICCV (2009)Google Scholar
  11. 11.
    Huang, C., Zhu, S., Yu, K.: Large scale strongly supervised ensemble metric learning, with applications to face verification and retrieval. arXiv 1212.6094 (2012)Google Scholar
  12. 12.
    Huang, D., Storer, M., De la Torre, F., Bischof, H.: Supervised local subspace learning for continuous head pose estimation. In: CVPR (2011)Google Scholar
  13. 13.
    Huang, G.B., Jain, V., Learned-Miller, E.: Unsupervised joint alignment of complex images. In: ICCV (2007)Google Scholar
  14. 14.
    Huang, G.B., Jones, M.J., Learned-Miller, E.: LFW results using a combined Nowak plus MERL recognizer. In: Real-Life Images Workshop at the ECCV (2008)Google Scholar
  15. 15.
    Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Tech. rep., University of Massachusetts, Amherst (2007)Google Scholar
  16. 16.
    James, W., Stein, J.: Estimation with quadratic loss. In: Berkeley Symposium on Mathematical Statistics and Probability (1961)Google Scholar
  17. 17.
    Kostinger, M., Hirzer, M., Wohlhart, P., Roth, P.M., Bischof, H.: Large scale metric learning from equivalence constraints. In: CVPR (2012)Google Scholar
  18. 18.
    Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In: CVPR (2011)Google Scholar
  19. 19.
    Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Attribute and simile classifiers for face verification. In: ICCV (2009)Google Scholar
  20. 20.
    Li, H., Hua, G., Lin, Z., Brandt, J., Yang, J.: Probabilistic elastic matching for pose variant face verification. In: CVPR (2013)Google Scholar
  21. 21.
    Li, X., Shen, C., Shi, Q., Dick, A., van den Hengel, A.: Non-sparse linear representations for visual tracking with online reservoir metric learning. In: CVPR (2012)Google Scholar
  22. 22.
    Li, Z., Cao, L., Chang, S., Smith, J.R., Huang, T.S.: Beyond mahalanobis distance: Learning second-order discriminant function for people verification. In: CVPR Workshops (2012)Google Scholar
  23. 23.
    Li, Z., Chang, S., Liang, F., Huang, T.S., Cao, L., Smith, J.R.: Learning locally-adaptive decision functions for person verification. In: CVPR (2013)Google Scholar
  24. 24.
    Lim, D., Mcfee, B., Lanckriet, G.R.: Robust structural metric learning. In: ICML (2013)Google Scholar
  25. 25.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar
  26. 26.
    Mensink, T., Verbeek, J., Perronnin, F., Csurka, G.: Metric learning for large scale image classification: Generalizing to new classes at near-zero cost. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 488–501. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  27. 27.
    Mignon, A., Jurie, F.: Pcca: A new approach for distance learning from sparse pairwise constraints. In: CVPR (2012)Google Scholar
  28. 28.
    Nowak, E., Jurie, F.: Learning visual similarity measures for comparing never seen objects. In: CVPR (2007)Google Scholar
  29. 29.
    Parameswaran, S., Weinberger, K.: Large margin multi-task metric learning. In: NIPS (2010)Google Scholar
  30. 30.
    Shen, C., Kim, J., Wang, L.: A scalable dual approach to semidefinite metric learning. In: CVPR (2011)Google Scholar
  31. 31.
    Shen, C., Kim, J., Wang, L., van den Hengel, A.: Positive semidefinite metric learning with boosting. In: NIPS (2009)Google Scholar
  32. 32.
    Simonyan, K., Parkhi, O.M., Vedaldi, A., Zisserman, A.: Fisher Vector Faces in the Wild. In: BMVC (2013)Google Scholar
  33. 33.
    Verma, Y., Jawahar, C.V.: Image annotation using metric learning in semantic neighbourhoods. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 836–849. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  34. 34.
    Weinberger, K.Q., Saul, L.K.: Fast solvers and efficient implementations for distance metric learning. In: ICML (2008)Google Scholar
  35. 35.
    Weinberger, K., Blitzer, J., Saul, L.: Distance metric learning for large margin nearest neighbor classification. In: NIPS (2006)Google Scholar
  36. 36.
    Wolf, L., Hassner, T., Taigman, Y.: Descriptor based methods in the wild. In: Real-Life Images Workshop at the ECCV (2008)Google Scholar
  37. 37.
    Ying, Y., Huang, K., Campbell, C.: Sparse metric learning via smooth optimization. In: NIPS (2009)Google Scholar
  38. 38.
    Ying, Y., Li, P.: Distance metric learning with eigenvalue optimization. J. Mach. Learn. Res. 13(1), 1–26 (2012)zbMATHMathSciNetGoogle Scholar
  39. 39.
    Zhou, X., Cui, N., Li, Z., Liang, F., Huang, T.S.: Hierarchical gaussianization for image classification. In: ICCV (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Qilong Wang
    • 1
    • 3
  • Wangmeng Zuo
    • 2
  • Lei Zhang
    • 3
  • Peihua Li
    • 1
  1. 1.School of Information and Communications EngineeringDalian University of TechnologyChina
  2. 2.School of Computer Science and TechnologyHarbin Institute of TechnologyChina
  3. 3.Department of ComputingHong Kong Polytechnic UniversityHong Kong

Personalised recommendations