Advertisement

Strict Subspace and Label-Space Structure for Domain Adaptation

  • Ying Li
  • Pei Zhang
  • Lin Cheng
  • Yaxin Peng
  • Chaomin ShenEmail author
Conference paper
  • 883 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11775)

Abstract

One of the most important issues of transfer learning is domain adaptation which aims at adapting a classifier or model trained in the source domain for use in the target domain, while two domains may be different but related. Intuitively, a good feature representation across domain is crucial. In this paper, we put forward a novel feature representation approach for unsupervised domain adaptation, namely Strict Subspace and Label-space Structure for Domain Adaptation (SSLS). SSLS learns two feature representations that project the source domain and target domain into two different subspaces where marginal and conditional distribution shift can be reduced effectively. Specially, we make the distances of corresponding points in the projection subspaces as well as the label space close by Laplacian graph, which will guarantee the strictness of subspace structure and the quality of the pseudo labels. Extensive experiments verify that our method is superior to several state-of-the-art methods on three real world cross-domain visual recognition tasks Office+Caltech, USPS+MNIST, and PIE.

Keywords

Transfer learning Unsupervised Domain adaptation Laplacian graph 

References

  1. 1.
    Pan, S.J., Yang, Q., et al.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  2. 2.
    Wang, H., Nie, F., Huang, H., Ding, C.H.: Dyadic transfer learning for cross-domain image classification. In: International Conference on Computer Vision, vol. 2011, pp. 551–556 (2011)Google Scholar
  3. 3.
    Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: International Conference on Computer Vision, vol. 2011, pp. 999–1006 (2011)Google Scholar
  4. 4.
    Qui, Q., Patel, V.M., Turage, P.K., Chellappa, R.: Domain adaptive dictionary learning. In: European Conference on Computer Vision, vol. 2012, pp. 631–645 (2012)Google Scholar
  5. 5.
    Chen, M., Xu, Z., Sha, F.: Marginalized denoising autoencoders for domain adaptation. In: International Conference on Machine Learning, vol. 2012, pp. 1627–1634 (2012)Google Scholar
  6. 6.
    Chidlovskii, B., Clinchant, S., Csurka, G.: Domain adaptation in the absence of source domain data. Knowl. Discov. Data Min. 2016, 451–460 (2016)Google Scholar
  7. 7.
    Yamada, M., Sigal, L., Raptis, M.: Covariate shift adaptation for discriminative 3D pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. 36(2), 235–247 (2014)CrossRefGoogle Scholar
  8. 8.
    Ying, S., Wen, Z., Shi, J., Peng, Y., Qiao, J.: Manifold preserving: an intrinsic approach for semisupervised distance metric learning. IEEE Trans. Neural Netw. Learn. Syst. 29(7), 2731–2742 (2018)MathSciNetGoogle Scholar
  9. 9.
    Yang, C., Zhang, L., Lu, H., Ruan, X., Yang, M.H.: Saliency detection via graph-based manifold ranking. In: Computer Vision and Pattern Recognition, vol. 2013, pp. 3166–3173 (2013)Google Scholar
  10. 10.
    Luo, L., Wang, X., Hu, S., Wang, C., Chen, L.: Close yet distinctive domain adaptation. In: Computer Vision and Pattern Recognization (2017)Google Scholar
  11. 11.
    Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Networks 22(2), 199–210 (2011)CrossRefGoogle Scholar
  12. 12.
    Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: International Conference on Computer Vision, vol. 2013, pp. 2200–2207 (2013)Google Scholar
  13. 13.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: Computer Vision and Pattern Recognition, vol. 2012, pp. 2066–2073 (2012)Google Scholar
  14. 14.
    Li, Y., Cheng, L., Peng Y., Wen Z., Ying S.: Manifold alignment and distribution adaptation for domain adaptation. In: Accepted by International Conference on Multimedia and Expo (2019)Google Scholar
  15. 15.
    Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: International Conference on Computer Vision, vol. 2013, pp. 2960–2967 (2013)Google Scholar
  16. 16.
    Sun, B., Saenko, K.: Subspace distribution alignment for unsupervised domain adaptation. In: British Machine Vision Conference (2015)Google Scholar
  17. 17.
    Zhang, J., Li, W., Ogunbona, P.: Joint geometrical and statistical alignment for visual domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  18. 18.
    Long, M., Cao, Y., Wang, J.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97–105 (2015)Google Scholar
  19. 19.
    Long, M., Zhu, H., Wang, J., Jordan, M. I.: Deep transfer learning with joint adaptation networks. In: International Conference on Machine Learning, pp. 2208–2217 (2017)Google Scholar
  20. 20.
    Lecun, Y.L., Bottou, L., Bengio, Y.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  21. 21.
    Hull, J.J.: A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 550–554 (1994)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ying Li
    • 1
  • Pei Zhang
    • 1
  • Lin Cheng
    • 1
  • Yaxin Peng
    • 2
  • Chaomin Shen
    • 3
    Email author
  1. 1.School of Computer Engineering and ScienceShanghai UniversityShanghaiChina
  2. 2.Department of Mathematics, School of ScienceShanghai UniversityShanghaiChina
  3. 3.Department of Computer ScienceEast China Normal UniversityShanghaiChina

Personalised recommendations