Discriminative Subspace Alignment for Unsupervised Visual Domain Adaptation (original) (raw)

Abstract

We address the problem of unsupervised visual domain adaptation for transferring category models from one visual domain or image data set to another. We present a new unsupervised domain adaptation algorithm based on subspace alignment. The core idea of our approach is to reduce the discrepancy between the source domain and the target domain in a latent discriminative subspace. Specifically, we first generate pseudo-labels for the target data by applying spectral clustering to a cross-domain similarity matrix, which is built from sparse coefficients found in a low-dimensional latent space. This coarse alignment between the two domains exploits the assumption that the collection of data of different classes from both domains can be viewed as samples from a union of low-dimensional subspaces. Then, we create discriminative subspaces for both domains using partial least squares correlation. Finally, a mapping which aligns the discriminative source subspace into the target one is learned by minimizing a Bregman matrix divergence function. Experimental results on benchmark cross-domain visual object recognition data sets and cross-view scene classification data sets demonstrate that the proposed method outperforms the baselines and several state-of-the-art competing methods.

Access this article

Log in via an institution

Subscribe and save

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset (technical report), Caltech
  2. Xiao J, Ehinger K, Hays J, Torralba A, Oliva A (2014) SUN database: exploring a large collection of scene categories. Int J Comput Vis 108:1–8
    Article MathSciNet Google Scholar
  3. Gong B, Grauman K, Sha F (2014) Learning kernels for unsupervised domain adaptation with applications to visual object recognition. Int J Comput Vis 109:3–27
    Article MathSciNet MATH Google Scholar
  4. Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: Proceedings of IEEE conference on computer vision and pattern recognition, vol 2, pp 2169–2178
  5. Dai D, Yang W (2011) Satellite image classification via two-layer sparse coding with biased image representation. IEEE Geosci Remote Sens Lett 8(1):173–176
    Article Google Scholar
  6. Yang Y, Newsam S (2010) Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the ACM international conference on Advances in geographic information systems, ACM, New York, pp 270–279
  7. Torralba A, Efros A (2011) Unbiased look at dataset bias. In: Proceedings of IEEE conference on computer vision and pattern recognition, vol 2, pp 1521–1528
  8. Margolis A (2011) A literature review of domain adaptation with unlabeled data (technical report), University of Washington, Washington
  9. Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359
    Article Google Scholar
  10. Shao L, Zhu F, Li X (2014) Transfer learning for visual categorization: a survey. IEEE TNNLS 26:1019–1034
    MathSciNet Google Scholar
  11. Patel VM, Gopalan R, Li R, Chellappa R (2015) Visual domain adaptation: an overview of recent advances. In: IEEE signal processing magazine
  12. Si S, Tao D, Geng B (2010) Bregman divergence-based regularization for transfer subspace learning. IEEE Trans Knowl Data Eng 22(7):929–942
    Article Google Scholar
  13. Tuia D, Volpi M, Trolliet M, Camps-Valls G (2014) Semisupervised manifold alignment of multimodal remote sensing images. IEEE Trans Geosci Remote Sens 52(12):7708–7720
    Article Google Scholar
  14. Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210
    Article Google Scholar
  15. Chang SF (2012) Robust visual domain adaptation with low-rank reconstruction. In: Proceedings of IEEE conference on computer vision and pattern recognition, vol 2, pp 1–8
  16. Shao M, Kit D, Fu Y (2014) Generalized transfer subspace learning through low-rank constraint. Int J Comput Vis 109:74–93
    Article MathSciNet MATH Google Scholar
  17. Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: an unsupervised approach. In: Proceedings of IEEE international conference on computer vision, pp 999–1006
  18. Baktashmotlagh M, Harandi MT, Lovell BC, Salzmann M (2013) Unsupervised domain adaptation by domain invariant projection. In: Proceedings of IEEE international conference on computer vision, pp 769–776
  19. Fernando B, Habrard A, Sebban M, Tuytelaars T (2013) Unsupervised visual domain adaptation using subspace alignment. In: Proceedings of IEEE international conference on computer vision, pp 2960–2967
  20. Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Wortman J (2010) A theory of learning from different domains. Mach Learn 79:151–175
    Article MathSciNet Google Scholar
  21. Elhamifar E, Vidal R (2013) Sparse subspace clustering: algorithm, theory, and applications. IEEE Trans Pattern Anal Mach Intell 35(11):2765–2781
    Article Google Scholar
  22. Patel VM, Nguyen HV, Vidal R (2013) Latent space sparse subspace clustering. In: Proceedings of IEEE international conference on computer vision, pp 225–232
  23. Levina E, Bickel PJ (2004) Maximum likelihood estimation of intrinsic dimension. In: Proceedings of the NIPS, pp 1–8
  24. Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11):1–8
    MATH Google Scholar
  25. Risojevic V, Babic Z (2011) Aerial image classification using structural texture similarity. In: Proceedings of the IEEE international symposium on signal processing and information technology, pp 190–195

Download references

Acknowledgments

This work was supported in part by the National Natural Science Foundation of China under Grant 61303186 and by the Ph.D. Programs Foundation of Ministry of Education of China under Grant 20124307120013.

Author information

Authors and Affiliations

  1. College of Electronic Science and Engineering, National University of Defense Technology, Changsha, 410072, China
    Hao Sun, Shuai Liu & Shilin Zhou

Authors

  1. Hao Sun
  2. Shuai Liu
  3. Shilin Zhou

Corresponding author

Correspondence toHao Sun.

Rights and permissions

About this article

Cite this article

Sun, H., Liu, S. & Zhou, S. Discriminative Subspace Alignment for Unsupervised Visual Domain Adaptation.Neural Process Lett 44, 779–793 (2016). https://doi.org/10.1007/s11063-015-9494-6

Download citation

Keywords