Joint distinct subspace learning and unsupervised transfer classification for visual domain adaptation

Abstract

In many real-world knowledge transfer and transfer learning scenarios, the known common problem is distribution discrepancy (i.e., the difference in type, distribution and dimensionality of features) between source and target domains. In this paper, we introduce joint distinct subspace learning and unsupervised transfer classification for visual domain adaptation (JDSC) method, which is an iterative two-step framework. JDSC is based on hybrid of feature-based and classifier-based approaches that uses the feature-based techniques to tackle the challenge of domain shift and classifier-based techniques to learn a reliable model. In addition, for subspace alignment, weighted joint geometrical and statistical alignment is proposed to learn two coupled projections for mapping the source and target data into respective subspaces by accounting the importance of marginal and conditional distributions, differently. The proposed method has been evaluated on various real-world image datasets. JDSC gets 86.2% average classification accuracy on four standard domain adaptation benchmarks. The experiments demonstrate that our proposed method achieves a significant improvement compared to other state of the arts in average classification accuracy. Our source code is available at https://github.com/jtahmores/JDSC.

This is a preview of subscription content, access via your institution.

Fig. 1

References

  1. 1.

    Csurka, G.: Domain adaptation for visual applications: a comprehensive survey (2017). arXiv preprint arXiv:1702.05374

  2. 2.

    Tahmoresnezhad, J., Hashemi, S.: Common feature extraction in multi-source domains for transfer learning. In: 2015 7th Conference on Information and Knowledge Technology (IKT), pp. 1–5 (2015)

  3. 3.

    Tahmoresnezhad, J., Hashemi, S.: Exploiting kernel-based feature weighting and instance clustering to transfer knowledge across domains. Turk. J. Electr. Eng. Comput. Sci. 25, 292–307 (2017)

    Article  Google Scholar 

  4. 4.

    Zhang, J., Li, W., Ogunbona, P.: Joint geometrical and statistical alignment for visual domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1859–1867 (2017)

  5. 5.

    Azab, A.M., Toth, J., Mihaylova, L.S., Arvaneh, M.: A review on transfer learning approaches in brain–computer interface. In: Signal Processing and Machine Learning for Brain–Machine Interfaces, pp. 81–101. Institution of Engineering and Technology (2018)

  6. 6.

    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2066–2073 (2012)

  7. 7.

    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)

    Article  Google Scholar 

  8. 8.

    Hull, J.J.: A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16, 550–554 (1994)

    Article  Google Scholar 

  9. 9.

    Wang, J., Feng, W., Chen, Y., Yu, H., Huang, M., Yu, P.S.: Visual domain adaptation with manifold embedded distribution alignment. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 402–410 (2018)

  10. 10.

    Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression (PIE) database. In: Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition, pp. 53–58 (2002)

  11. 11.

    Asgarian, A., et al.: A hybrid instance-based transfer learning method (2018). arXiv preprint arXiv:1812.01063

  12. 12.

    Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big Data 3, 9 (2016)

    Article  Google Scholar 

  13. 13.

    Ghifary, M., Balduzzi, D., Kleijn, W.B., Zhang, M.: Scatter component analysis: a unified framework for domain adaptation and domain generalization. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1414–1430 (2016)

    Article  Google Scholar 

  14. 14.

    Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2200–2207 (2013)

  15. 15.

    Mahadevan, S., Mishra, B., Ghosh, S.: A unified framework for domain adaptation using metric learning on manifolds. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 843–860. Springer (2018)

  16. 16.

    Rubin, J., et al.: An ensemble boosting model for predicting transfer to the pediatric intensive care unit. Int. J. Med. Inform. 112, 15–20 (2018)

    Article  Google Scholar 

  17. 17.

    Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: Advances in Neural Information Processing Systems, pp. 137–144 (2007)

  18. 18.

    Wang, J., Chen, Y., Hao, S., Feng, W., Shen, Z.: Balanced distribution adaptation for transfer learning. In: 2017 IEEE International Conference on Data Mining (ICDM), pp. 1129–1134. IEEE (2017)

  19. 19.

    Long, M., Wang, J., Ding, G., Pan, S.J., Philip, S.Y.: Adaptation regularization: a general framework for transfer learning. IEEE Trans. Knowl. Data Eng. 26, 1076–1089 (2013)

    Article  Google Scholar 

  20. 20.

    Xu, Y., Fang, X., Wu, J., Li, X., Zhang, D.: Discriminative transfer subspace learning via low-rank and sparse representation. IEEE Trans. Image Process. 25, 850–863 (2015)

    MathSciNet  Article  Google Scholar 

  21. 21.

    Li, S., Song, S., Huang, G., Ding, Z., Wu, C.: Domain invariant and class discriminative feature learning for visual domain adaptation. IEEE Trans. Image Process. 27, 4260–4273 (2018)

    MathSciNet  Article  Google Scholar 

  22. 22.

    Tahmoresnezhad, J., Hashemi, S.: Visual domain adaptation via transfer feature learning. Knowl. Inf. Syst. 50, 585–605 (2017)

    Article  Google Scholar 

  23. 23.

    Sun, B., Saenko, K.: Deep coral: correlation alignment for deep domain adaptation. In: European Conference on Computer Vision Workshops, pp. 443–450 (2016)

  24. 24.

    Huang, J., Zhou, Z.: Transfer metric learning for unsupervised domain adaptation. IET Image Proc. 13, 804–810 (2019)

    Article  Google Scholar 

  25. 25.

    Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., Liu, C.: A survey on deep transfer learning. In: International Conference on Artificial Neural Networks, pp. 270–279 (2018)

  26. 26.

    Addabbo, P., Focareta, M., Marcuccio, S., Votto, C., Ullo, S.L.: Land cover classification and monitoring through multisensor image and data combination. In: 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 902–905 (2016)

  27. 27.

    Addabbo, P., Angrisano, A., Bernardi, M.L., Gagliarde, G., Mennella, A., Nisi, M., Ullo, S.L.: UAV system for photovoltaic plant inspection. IEEE Aerosp. Electron. Syst. Mag. 33, 58–67 (2018)

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Jafar Tahmoresnezhad.

Ethics declarations

Conflicts of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Noori Saray, S., Tahmoresnezhad, J. Joint distinct subspace learning and unsupervised transfer classification for visual domain adaptation. SIViP 15, 279–287 (2021). https://doi.org/10.1007/s11760-020-01745-w

Download citation

Keywords

  • Transfer learning
  • Domain adaptation
  • Subspace alignment
  • Classification
  • Distribution discrepancy