Advertisement

Guided Learning: A New Paradigm for Multi-task Classification

  • Jingru Fu
  • Lei Zhang
  • Bob Zhang
  • Wei Jia
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10996)

Abstract

A prevailing problem in many machine learning tasks is that the training and test data have different distribution (non i.i.d). Previous methods to solve this problem are called Transfer Learning (TL) or Domain Adaptation (DA), which belong to one stage models. In this paper, we propose a new, simple but effective paradigm, Guided Learning (GL), for multi-stage progressive training. This new paradigm is motivated by the “tutor guides student” learning mode in human world. Further, under the framework of GL, a Guided Subspace Learning (GSL) method is proposed for domain disparity reduction, which aims to learn an optimal, invariant and discriminative subspace through the guided learning strategy. Extensive experiments on various databases show that our method outperforms many state-of-the-art TL/DA methods.

Keywords

Guided Learning Subspace Learning Domain disparity 

Notes

Acknowledgements

This work was supported by the National Science Fund of China under Grants (61771079).

References

  1. 1.
    Jian Feng Cai, C., Emmanuel, J.S., Shen, Z.: A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20(4), 1956–1982 (2008)MathSciNetzbMATHGoogle Scholar
  2. 2.
    Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: IEEE ICCV, pp. 2960–2967 (2014)Google Scholar
  3. 3.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: IEEE CVPR, pp. 2066–2073 (2012)Google Scholar
  4. 4.
    Hong Jhuo, I, Liu, D., Lee, D.T., Chang, S.F.: Robust visual domain adaptation with low-rank reconstruction. In: CVPR, pp. 2168–2175 (2012)Google Scholar
  5. 5.
    Kan, M., Junting, W., Shan, S., Chen, X.: Domain adaptation for face recognition: targetize source domain bridged by common subspace. IJCV 109(1–2), 94–109 (2014)CrossRefGoogle Scholar
  6. 6.
    Lei, Z., Zhang, D.: Robust visual knowledge transfer via extreme learning machine-based domain adaptation. IEEE Trans. IP 25(10), 4959–4973 (2016)MathSciNetGoogle Scholar
  7. 7.
    Long, M., Wang, J., Ding, G., Sun, J., Yu P.S.: Transfer feature learning with joint distribution adaptation. In: IEEE ICCV, pp. 2200–2207 (2014)Google Scholar
  8. 8.
    Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer joint matching for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1410–1417 (2014)Google Scholar
  9. 9.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  10. 10.
    Shao, M., Kit, D., Yun, F.: Generalized transfer subspace learning through low-rank constraint. IJCV 109(1–2), 74–93 (2014)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Si, S., Tao, D., Geng, B.: Bregman divergence-based regularization for transfer subspace learning. IEEE Trans. Knowl. Data Eng. 22(7), 929–942 (2010)CrossRefGoogle Scholar
  12. 12.
    Sun, B., Feng, J., Saenko, K.: Correlation alignment for unsupervised domain adaptation. In: Csurka, G. (ed.) Domain Adaptation in Computer Vision Applications. ACVPR, pp. 153–171. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-58347-1_8CrossRefGoogle Scholar
  13. 13.
    Sun, B., Saenko, K.: Subspace distribution alignment for unsupervised domain adaptation. In: BMVC, pp. 24.1–24.10 (2015)Google Scholar
  14. 14.
    Wright, J., Ganesh, A., Rao, S., Ma, Y.: Robust principal component analysis: exact recovery of corrupted low-rank matrices. J. ACM 87(4), 20:3–20:56 (2009)Google Scholar
  15. 15.
    Xu, Y., Fang, X., Wu, J., Li, X., Zhang, D.: Discriminative transfer subspace learning via low-rank and sparse representation. IEEE Trans. IP 25(2), 850–863 (2016)MathSciNetGoogle Scholar
  16. 16.
    Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive SVMS. In: ACM International Conference on Multimedia, pp. 188–197 (2007)Google Scholar
  17. 17.
    Zhang, L., Zuo, W., Zhang, D.: LSDT: latent sparse domain transfer learning for visual adaptation. IEEE Trans. IP 25(3), 1177–1191 (2016)MathSciNetGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.College of Communication EngineeringChongqing UniversityChongqingChina
  2. 2.Department of Computer and Information ScienceUniversity of MacauMacauChina
  3. 3.School of Computer and InformationHefei University of TechnologyHefeiChina

Personalised recommendations