Domain Adaptation with a Domain Specific Class Means Classifier

  • Gabriela CsurkaEmail author
  • Boris Chidlovskii
  • Florent Perronnin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8927)


We consider the problem of learning a classifier when we dispose little training data from the target domain but abundant training data from several source domains. We make two contributions to the domain adaptation problem. First we extend the Nearest Class Mean (NCM) classifier by introducing for each class domain-dependent mean parameters as well as domain-specific weights. Second, we propose a generic adaptive semi-supervised metric learning technique that iteratively curates the training set by adding unlabeled samples with high prediction confidence and by removing labeled samples for which the prediction confidence is low. These two complementary techniques are evaluated on two public benchmarks: the ImageClef Domain Adaptation Challenge and the Office-CalTech datasets. Both contributions are shown to yield improvements and to be complementary to each other.


Domain adaptation Self-adative metric learning NCM 


  1. 1.
    Baktashmotlagh, M., Harandi, M.T., Lovell, B.C., Salzmann, M.: Unsupervised domain adaptation by domain invariant projection. In: ICCV (2013)Google Scholar
  2. 2.
    Beijbom, O.: Domain adaptations for computer vision applications. University of California, San Diego (June (2012)Google Scholar
  3. 3.
    Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: SLCV (ECCV Workshop) (2004)Google Scholar
  4. 4.
    Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML (2007)Google Scholar
  5. 5.
    Duan, L., Tsang, I.W., Xu, D., Maybank, S.J.: Domain transfer SVM for video concept detection. In: CVPR (2009)Google Scholar
  6. 6.
    Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: ICCV (2013)Google Scholar
  7. 7.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)Google Scholar
  8. 8.
    Gong, B., Grauman, K., Sha, F.: Reshaping visual datasets for domain adaptation. In: NIPS (2013)Google Scholar
  9. 9.
    Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: ICCV (2011)Google Scholar
  10. 10.
    Hoffman, J., Kulis, B., Darrell, T., Saenko, K.: Discovering Latent Domains for Multisource Domain Adaptation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 702–715. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  11. 11.
    Huang, J., Smola, A., A., Borgwardt, K., Schoelkopf, B.: Correcting sample selection bias by unlabeled data. In: NIPS (2007)Google Scholar
  12. 12.
    Jiang, J.: A literature survey on domain adaptation of statistical classifiers. Tech. rep. (2008)Google Scholar
  13. 13.
    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
  14. 14.
    Mensink, T., Verbeek, J., Perronnin, F., Csurka, G.: Distance-based image classification: Generalizing to new classes at near zero cost. PAMI 35(11), 2624–2637 (2013)CrossRefGoogle Scholar
  15. 15.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  16. 16.
    Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher Kernel for Large-Scale Image Classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  17. 17.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting Visual Category Models to New Domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  18. 18.
    Saha, A., Rai, P., Daumé III, H., Venkatasubramanian, S., DuVall, S.L.: Active Supervised Domain Adaptation. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part III. LNCS, vol. 6913, pp. 97–112. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  19. 19.
    Tommasi, T., Caputo, B.: Frustratingly easy nbnn domain adaptation. In: ICCV (2013)Google Scholar
  20. 20.
    Weinberger, K., Saul, L.: Distance metric learning for large margin nearest neighbor classification. JMLR 10, 207–244 (2009)zbMATHGoogle Scholar
  21. 21.
    Zha, Z.J., Mei, T., Wang, M., Wang, Z., Hua, X.S.: Robust distance metric learning with auxiliary knowledge. In: IJCAI (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Gabriela Csurka
    • 1
    Email author
  • Boris Chidlovskii
    • 1
  • Florent Perronnin
    • 1
  1. 1.Xerox Research Centre EuropeMeylanFrance

Personalised recommendations