KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Domain Adaptation Image Classification Based on Multi-sparse Representation

  • Zhang, Xu (College of Electronic Information Engineering, Suzhou Vocational University) ;
  • Wang, Xiaofeng (Department of Computer Science and Technology, Hefei University) ;
  • Du, Yue (Sixth Department, Army Officer Academy of PLA) ;
  • Qin, Xiaoyan (Eleventh Department, Army Officer Academy of PLA)
  • Received : 2016.08.10
  • Accepted : 2016.10.03
  • Published : 2017.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Generally, research of classical image classification algorithms assume that training data and testing data are derived from the same domain with the same distribution. Unfortunately, in practical applications, this assumption is rarely met. Aiming at the problem, a domain adaption image classification approach based on multi-sparse representation is proposed in this paper. The existences of intermediate domains are hypothesized between the source and target domains. And each intermediate subspace is modeled through online dictionary learning with target data updating. On the one hand, the reconstruction error of the target data is guaranteed, on the other, the transition from the source domain to the target domain is as smooth as possible. An augmented feature representation produced by invariant sparse codes across the source, intermediate and target domain dictionaries is employed for across domain recognition. Experimental results verify the effectiveness of the proposed algorithm.

Keywords

References

  1. L Nie, M Wang, Z J Zha and T S Chua, "Oracle in Image Search: A Content-Based Approach to Performance Prediction," Acm Transactions on Information Systems, vol. 30, iss. 2, pp.1-23, May, 2012.
  2. R C Hong, M Wang, Y Gao, D C Tao, X L Li and X D Wu, "Image Annotation by Multiple-Instance Learning With Discriminative Feature Mapping and Selection," IEEE Transactions on Cybernetics, vol. 44, no. 5, pp.669-680, June,2013. https://doi.org/10.1109/TCYB.2013.2265601
  3. L Nie, M Wang, Z Zha, G Li and T S Chua, "Multimedia answering: enriching text QA with media information," in Proc. of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, pp. 695-704, July 24-28, 2011.
  4. S Lazebnik, C Schmid and J Ponce, "Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories," in Proc. of 2006 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, Vol.2, pp.2169-2178, June 17-22, 2006.
  5. J Yang, K Yu, Y Gong and T Huang, "Linear spatial pyramid matching using sparse coding for image classification," in Proc. of 2009 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 1794-1801,June 20-25, 2009.
  6. J Wang, J Yang, K Yu and F Lv, "Locality-constrained linear coding for image classification," in Proc. of 2010 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 3360-3367, June 13-18,2010.
  7. R Chellappa, J Ni and V M Patel, "Remote identification of faces: Problems, prospects, and progress," Pattern Recognition Letters, vol. 33, iss. 14, pp. 1849-1859, October, 2012. https://doi.org/10.1016/j.patrec.2011.11.020
  8. A Torralba and A A Efros, "Unbiased look at dataset bias," in Proc. of 2011 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 1521-1528, June 20-25, 2011.
  9. M Kan, J Wu, S Shan and X Chen, "Domain Adaptation for Face Recognition: Targetize Source Domain Bridged by Common Subspace," International Journal of Computer Vision, vol. 109, iss. 1, pp. 94-109, August, 2014. https://doi.org/10.1007/s11263-013-0693-1
  10. S Bendavid, J Blitzer, K Crammer, A Kulesza and F Pereira, "A theory of learning from different domains," Machine learning, vol. 79, iss. 1, pp. 151-175, May, 2010. https://doi.org/10.1007/s10994-009-5152-4
  11. S. J. Pan, Q Yang, "A Survey on Transfer Learning," IEEE Transactions on Knowledge & Data Engineering, vol. 22, iss. 10, pp. 1345-1359, October, 2010. https://doi.org/10.1109/TKDE.2009.191
  12. Z c Li, J Liu, J H Tang and H Q Lu, "Robust Structured Subspace Learning for Data Representation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.37, iss.10, pp.2085-2098, October, 2015. https://doi.org/10.1109/TPAMI.2015.2400461
  13. D. L. Donoho, "Compressed sensing," IEEE Transactions on Information Theory, vol. 52, iss. 4, pp. 1289-1306, April, 2006. https://doi.org/10.1109/TIT.2006.871582
  14. J. J. Heckman, "Sample selection bias as a specification error," Applied Econometrics, vol. 31, no. 1, pp. 153-61 2013.
  15. B Scholkopf, J Platt and T Hofmann, "Correcting Sample Selection Bias by Unlabeled Data," in Proc. of Conference on Advances in Neural Information Processing Systems, pp. 601-608, December 3-6, 2007.
  16. K Saenko, B Kulis, M Fritz and T Darrell, "Adapting visual category models to new domains," in Proc. of 11th European conference on Computer vision, pp.213-226, September 5-11, 2010.
  17. R Gopalan, R Li and R Chellappa, "Domain adaptation for object recognition: An unsupervised approach," in Proc. of 2011 IEEE International Conference on Computer Vision, pp.999-1006. November 6-13, 2011.
  18. F Sha, Y Shi, B Gong and K Grauman, "Geodesic flow kernel for unsupervised domain adaptation," in Proc. of 2012 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 2066-2073, June 16-21, 2012.
  19. IH Jhuo, D Liu, DT Lee and SF Chang, "Robust visual domain adaptation with low-rank reconstruction," in Proc. of 2012 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 2168-2175, June 16-21, 2012.
  20. J Ni, Q Qiu and R Chellappa, "Subspace interpolation via dictionary learning for unsupervised domain adaptation," in Proc. of 2013 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 692-699 , June 25-27, 2013.
  21. S J Pan, J T Kwok and Q Yang, "Transfer Learning via Dimensionality Reduction," in Proc. of the Twenty-Third Aaai Conference on Artificial Intelligence, pp. 677-682, July 13-17,2008.
  22. S J Pan, IW Tsang, JT Kwok and Q Yang, "Domain adaptation via transfer component analysis," IEEE Transactions on Neural Networks, vol.22, iss.2, pp.199-210, February, 2011. https://doi.org/10.1109/TNN.2010.2091281
  23. J Yang, R Yan and A G Hauptmann, "Cross-domain video concept detection using adaptive svms," in Proc. of 15th ACM international conference on Multimedia, pp.188-197, September 23-28, 2007.
  24. L Bruzzone and M Marconcini, "Toward the automatic updating of land-cover maps by a domain-adaptation SVM classifier and a circular validation strategy," IEEE Transactions on Geoscience & Remote Sensing, vol.47, iss.4, pp. 1108-1122, April, 2009. https://doi.org/10.1109/TGRS.2008.2007741
  25. A Wagner, J Wright, A Ganesh, Z Zhou, H Mobahi and Y Ma, "Toward a practical face recognition system: Robust alignment and illumination by sparse representation," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.34, iss.2, pp.372-386, February, 2012. https://doi.org/10.1109/TPAMI.2011.112
  26. C Zhao, X Wang and W K Cham, "Background subtraction via robust dictionary learning," EURASIP Journal on Image and Video Processing, vol.2011, no.10, pp.2919-2929, February, 2011.
  27. J Mairal, F Bach, J Ponce and G Sapiro, "Online learning for matrix factorization and sparse coding," Journal of Machine Learning Research, vol.11, no.1, pp.19-60, March, 2010.
  28. A Bergamo and L Torresani, "Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach," in Proc. of Advances in Neural Information Processing Systems 23, pp. 181-189, December 6-9, 2010.
  29. O Boiman, E Shechtman and M Irani, "In defense of nearest-neighbor based image classification," in Proc. of 2013 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 1-8, June 23-28, 2008.
  30. T Tommasi and B Caputo, "Frustratingly easy nbnn domain adaptation," in Proc. of 2013 IEEE International Conference on Computer Vision, pp. 897-904, December 1-8, 2013.
  31. C Lu, J Shi and J Jia, "Online robust dictionary learning," in Proc. of 2013 IEEE Computer Society Conference on Computer Vision & Pattern Recognition, pp. 415-422, June 23-28, 2013.