Advertisement

Exploiting Low-Rank Structure from Latent Domains for Domain Generalization

  • Zheng Xu
  • Wen Li
  • Li Niu
  • Dong Xu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8691)

Abstract

In this paper, we propose a new approach for domain generalization by exploiting the low-rank structure from multiple latent source domains. Motivated by the recent work on exemplar-SVMs, we aim to train a set of exemplar classifiers with each classifier learnt by using only one positive training sample and all negative training samples. While positive samples may come from multiple latent domains, for the positive samples within the same latent domain, their likelihoods from each exemplar classifier are expected to be similar to each other. Based on this assumption, we formulate a new optimization problem by introducing the nuclear-norm based regularizer on the likelihood matrix to the objective function of exemplar-SVMs. We further extend Domain Adaptation Machine (DAM) to learn an optimal target classifier for domain adaptation. The comprehensive experiments for object recognition and action recognition demonstrate the effectiveness of our approach for domain generalization and domain adaptation.

Keywords

Latent domains domain generalization domain adaptation exemplar-SVMs 

References

  1. 1.
    Argyriou, A., Evgeniou, T., Pontil, M.: Multi-task feature learning. NIPS (2007)Google Scholar
  2. 2.
    Baktashmotlagh, M., Harandi, M., Brian Lovell, M.S.: Unsupervised domain adaptation by domain invariant projection. In: ICCV (2013)Google Scholar
  3. 3.
    Bruzzone, L., Marconcini, M.: Domain adaptation problems: A DASVM classification technique and a circular validation strategy. T-PAMI 32(5), 770–787 (2010)CrossRefGoogle Scholar
  4. 4.
    Cai, J., Cands, E.J., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM Journal on Optimization 20(4), 1956–1982 (2010)CrossRefzbMATHMathSciNetGoogle Scholar
  5. 5.
    Chen, J., Zhou, J., Ye, J.: Integrating low-rank and group-sparse structures for robust multi-task learning. In: SIGKDD (2011)Google Scholar
  6. 6.
    Chen, L., Duan, L., Xu, D.: Event recognition in videos by learning from heterogeneous web sources. In: CVPR, pp. 2666–2673 (2013)Google Scholar
  7. 7.
    Chen, L., Li, W., Xu, D.: Recognizing RGB images by learning from RGB-D data. In: CVPR, pp. 1418–1425 (2014)Google Scholar
  8. 8.
    Chu, W.S., la Torre, F.D., Cohn, J.F.: Selective transfer machine for personalized facial action unit detection. In: CVPR (2013)Google Scholar
  9. 9.
    Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: DeCAF: A deep convolutional activation feature for generic visual recognition. In: ICML (2014)Google Scholar
  10. 10.
    Duan, L., Xu, D., Tsang, I.W., Luo, J.: Visual event recognition in videos by learning from web data. T-PAMI 34(9), 1667–1680 (2012)CrossRefGoogle Scholar
  11. 11.
    Duan, L., Tsang, I.W., Xu, D.: Domain transfer multiple kernel learning. T-PAMI 34(3), 465–479 (2012)CrossRefGoogle Scholar
  12. 12.
    Duan, L., Xu, D., Chang, S.F.: Exploiting web images for event recognition in consumer videos: A multiple source domain adaptation approach. In: CVPR, pp. 1338–1345 (2012)Google Scholar
  13. 13.
    Duan, L., Xu, D., Tsang, I.W.: Domain adaptation from multiple sources: A domain-dependent regularization approach. T-NNLS 23(3), 504–518 (2012)Google Scholar
  14. 14.
    Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: ICCV (2013)Google Scholar
  15. 15.
    Gong, B., Grauman, K., Sha, F.: Reshaping visual datasets for domain adaptation. In: NIPS (2013)Google Scholar
  16. 16.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)Google Scholar
  17. 17.
    Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: ICCV (2011)Google Scholar
  18. 18.
    Gretton, A., Gorgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. JMLR 23, 723–773 (2012)Google Scholar
  19. 19.
    Hoai, M., Zisserman, A.: Discriminative sub-categorization. In: CVPR (2013)Google Scholar
  20. 20.
    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
  21. 21.
    Huang, J., Smola, A., Gretton, A., Borgwardt, K., Scholkopf, B.: Correcting sample selection bias by unlabeled data. In: NIPS (2007)Google Scholar
  22. 22.
    Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A.: Undoing the damage of dataset bias. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 158–171. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  23. 23.
    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
  24. 24.
    Li, W., Duan, L., Xu, D., Tsang, I.W.: Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. T-PAMI 36(6), 1134–1148 (2014)CrossRefGoogle Scholar
  25. 25.
    Malisiewicz, T., Gupta, A., Efros, A.A.: Ensemble of exemplar-SVMs for object detection and beyond. In: ICCV (2011)Google Scholar
  26. 26.
    Muandet, K., Balduzzi, D., Schölkopf, B.: Domain generalization via invariant feature representation. In: ICML (2013)Google Scholar
  27. 27.
    Recht, B., Fazel, M., Parrilo, P.A.: Guaranteed minimum rank solutions to linear matrix equations via nuclear norm minimization. SIAM Review 52(3), 471–501 (2010)CrossRefzbMATHMathSciNetGoogle Scholar
  28. 28.
    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
  29. 29.
    Wang, H., Kläser, A., Schmid, C., Liu, C.L.: Dense trajectories and motion boundary descriptors for action recognition. International Journal of Computer Vision 103(1), 60–79 (2013)CrossRefMathSciNetGoogle Scholar
  30. 30.
    Weinland, D., Boyer, E., Ronfard, R.: Action recognition from arbitrary views using 3d exemplars. In: ICCV (2007)Google Scholar
  31. 31.
    Xiao, S., Tan, M., Xu, D.: Weighted block-sparse low rank representation for face clustering in videos. In: ECCV (2014)Google Scholar
  32. 32.
    Xu, X., Tsang, I.W., Xu, D.: Soft margin multiple kernel learning. T-NN 24(5), 749–761 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Zheng Xu
    • 1
  • Wen Li
    • 1
  • Li Niu
    • 1
  • Dong Xu
    • 1
  1. 1.School of Computer EngineeringNanyang Technological UniversitySingapore

Personalised recommendations