Skip to main content
SpringerLink
Log in

Unsupervised visual domain adaptation via discriminative dictionary evolution

  • Theoretical advances
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

This work focuses on unsupervised visual domain adaptation which is still challenging in visual recognition. Most of the attention has been dedicated to seeking the domain-invariant features of cross-domain data, but they ignores the valuable discriminative information in the source domain. In this paper, we propose a Discriminative Dictionary Evolution (DDE) approach to seek discriminative features robust to domain shift. Specifically, DDE gradually adapts a discriminative dictionary learned from the source domain to the target domain through a dictionary evolving procedure, in which self-selected atoms of the dictionary are updated with \(\ell _{2,1}\)-norm-based regularization. DDE produces domain-invariant representations for cross-domain visual recognition meanwhile promotes the discriminativeness of the dictionary. Empirical results on real-world data sets demonstrate the advantages of the proposed approach over existing competitive methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

References

  1. Baktashmotlagh M, Harandi MT, Lovell BC, Salzmann M (2013) Unsupervised domain adaptation by domain invariant projection. In: ICCV, pp 769–776

  2. Baktashmotlagh M, Harandi MT, Lovell BC, Salzmann M (2014) Domain adaptation on the statistical manifold. In: CVPR, pp 2481–2488

  3. Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Mach Learn 79(1–2):151–175

    Article  MathSciNet  Google Scholar 

  4. Chen M, Weinberger K, Sha F, Bengio Y (2014) Marginalized denoising auto-encoders for nonlinear representations. In: ICML, pp 1476–1484

  5. Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T (2014) Decaf: a deep convolutional activation feature for generic visual recognition. In: ICML, pp 647–655

  6. Duan L, Tsang IW, Xu D (2012) Domain transfer multiple kernel learning. IEEE Trans Pattern Anal Mach Intell 34(3):465–479

    Article  Google Scholar 

  7. Duan L, Tsang IW, Xu D, Chua T (2009) Domain adaptation from multiple sources via auxiliary classifiers. In: ICML, pp 289–296

  8. Fernando B, Habrard A, Sebban M, Tuytelaars T (2013) Unsupervised visual domain adaptation using subspace alignment. In: ICCV, pp 2960–2967

  9. Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd international conference on machine learning, vol 37, pp 1180–1189

  10. Ghifary M, Kleijn WB, Zhang M, Balduzzi D, Li W (2016) Deep reconstruction-classification networks for unsupervised domain adaptation. In: ECCV, pp 597–613

  11. Gong B, Grauman K, Sha F (2014) Learning kernels for unsupervised domain adaptation with applications to visual object recognition. Int J Comput Vis 109(1–2):3–27

    Article  MathSciNet  Google Scholar 

  12. Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp 2066–2073

  13. Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: an unsupervised approach. In: ICCV, pp 999–1006

  14. Gopalan R, Li R, Chellappa R (2014) Unsupervised adaptation across domain shifts by generating intermediate data representations. IEEE Trans Pattern Anal Mach Intell 36(11):2288–2302

    Article  Google Scholar 

  15. Gretton A, Borgwardt KM, Rasch MJ, Schölkopf B, Smola A (2012) A kernel two-sample test. J Mach Learn Res 13:723–773

    MathSciNet  MATH  Google Scholar 

  16. Griffin G, Holub A, Perona P (2007) Caltech-256 Object Category Dataset. Tech. Rep, California Institute of Technology

  17. Gross R, Matthews I, Cohn JF, Kanade T, Baker S (2010) Multi-pie. Image Vis Comput 28(5):807–813

    Article  Google Scholar 

  18. Huang D, Wang YF (2013) Coupled dictionary and feature space learning with applications to cross-domain image synthesis and recognition. In: ICCV, pp 2496–2503

  19. Hull JJ (1994) A database for handwritten text recognition research. IEEE Trans Pattern Anal Mach Intell 16(5):550–554

    Article  Google Scholar 

  20. Jiang Z, Lin Z, Davis LS (2013) Label consistent K-SVD: learning a discriminative dictionary for recognition. IEEE Trans Pattern Anal Mach Intell 35(11):2651–2664

    Article  Google Scholar 

  21. Kan M, Wu J, Shan S, Chen X (2014) Domain adaptation for face recognition: targetize source domain bridged by common subspace. Int J Comput Vis 109(1–2):94–109

    Article  Google Scholar 

  22. Kulis B, Saenko K, Darrell T (2011) What you saw is not what you get: domain adaptation using asymmetric kernel transforms. In: CVPR, pp 1785–1792

  23. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, pp 2278–2324

  24. Li W, Duan L, Xu D, Tsang IW (2014) Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation. IEEE Trans Pattern Anal Mach Intell 36(6):1134–1148

    Article  Google Scholar 

  25. Long M, Ding G, Wang J, Sun J, Guo Y, Yu PS (2013) Transfer sparse coding for robust image representation. In: CVPR, pp 407–414

  26. Long M, Wang J, Cao Y, Sun J, Yu PS (2016) Deep learning of transferable representation for scalable domain adaptation. IEEE Trans Knowl Data Eng 28(8):2027–2040

    Article  Google Scholar 

  27. Long M, Wang J, Ding G, Sun J, Yu PS (2014) Transfer joint matching for unsupervised domain adaptation. In: CVPR, pp 1410–1417

  28. Long M, Wang J, Sun J, Yu PS (2015) Domain invariant transfer kernel learning. IEEE Trans Knowl Data Eng 27(6):1519–1532

    Article  Google Scholar 

  29. Long M, Zhu H, Wang J, Jordan MI (2016) Unsupervised domain adaptation with residual transfer networks. In: Advances in neural information processing systems, pp 136–144

  30. Lu H, Zhang L, Cao Z, Wei W, Xian K, Shen C, van den Hengel A (2017) When unsupervised domain adaptation meets tensor representations. In: ICCV, pp ​599–608

  31. Motiian S, Piccirilli M, Adjeroh DA, Doretto G (2017) Unified deep supervised domain adaptation and generalization. In: ICCV, pp 5715​–5725

  32. Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS

  33. Ni J, Qiu Q, Chellappa R (2013) Subspace interpolation via dictionary learning for unsupervised domain adaptation. In: CVPR, pp 692–699

  34. Pan SJ, Kwok JT, Yang Q (2008) Transfer learning via dimensionality reduction. In: AAAI, pp 677–682

  35. 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 

  36. Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  37. Patel V, Gopalan R, Li R, Chellappa R (2015) Visual domain adaptation: a survey of recent advances. IEEE Signal Process Magazine 32(3):53–69

    Article  Google Scholar 

  38. Qiu Q, Patel VM, Turaga PK, Chellappa R (2012) Domain adaptive dictionary learning. In: ECCV, pp 631–645

  39. Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: ECCV, pp 213–226

  40. Shekhar S, Patel VM, Nguyen HV, Chellappa R (2015) Coupled projections for adaptation of dictionaries. IEEE Trans Image Process 24(10):2941–2954

    Article  MathSciNet  Google Scholar 

  41. Shi Y, Sha F (2012) Information-theoretical learning of discriminative clusters for unsupervised domain adaptation. In: ICML, pp 1275​–1282

  42. Shu L, Ma T, Latecki LJ (2014) Locality preserving projection for domain adaptation with multi-objective learning. In: AAAI, pp 2085–2091

  43. Sun H, Liu S, Zhou S (2016) Discriminative subspace alignment for unsupervised visual domain adaptation. Neural Process Lett 44(3):779–793

    Article  Google Scholar 

  44. Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: CVPR, pp ​7167–7176

  45. Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014) Deep domain confusion: maximizing for domain invariance. ArXiv preprint arXiv:1412.3474 (2014)

  46. Volpi R, Morerio P, Savarese S, Murino V (2018) Adversarial feature augmentation for unsupervised domain adaptation. In: CVPR, pp 5495​–5504

  47. Wang J, Li X, Du J (2018) Label space embedding of manifold alignment for domain adaption. Neural Process Lett. https://doi.org/10.1007/s11063-018-9822-8

    Article  Google Scholar 

  48. Wu S, Jing XY, Yue D, Zhang J, Yang J, Yang J (2016) Unsupervised visual domain adaptation via dictionary evolution. In: 2016 IEEE international conference on multimedia and expo (ICME), pp 1–6

  49. Xiao M, Guo Y (2012) Semi-supervised kernel matching for domain adaptation. In: AAAI, pp 1183​–1189

  50. Xie X, Sun S, Chen H, Qian J (2017) Domain adaptation with twin support vector machines. Neural Process Lett. https://doi.org/10.1007/s11063-017-9775-3

    Article  Google Scholar 

  51. Xu X, Shimada A, Taniguchi R, He L (2015) Coupled dictionary learning and feature mapping for cross-modal retrieval. In: ICME, pp 1–6

  52. Xu Y, Fang X, Wu J, Li X, Zhang D (2016) Discriminative transfer subspace learning via low-rank and sparse representation. IEEE Trans Image Process 25(2):850–863

    Article  MathSciNet  Google Scholar 

  53. Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation. In: ICCV, pp 543–550

  54. Zadrozny B (2004) Learning and evaluating classifiers under sample selection bias. In: ICML, pp 114​–122

  55. Zelnik-Manor L, Perona P (2004) Self-tuning spectral clustering. In: NIPS, pp 1601–1608

  56. Zhang XY, Liu CL (2013) Writer adaptation with style transfer mapping. IEEE Trans Pattern Anal Mach Intell 35(7):1773–1787

    Article  Google Scholar 

  57. Zheng J, Jiang Z, Phillips PJ, Chellappa R (2012) Cross-view action recognition via a transferable dictionary pair. In: BMVC, pp 1–11

Download references

Funding

This work is supported by the National Natural Science Foundation of China under Grant Nos. 61402238, 61502245, 61972212; the Natural Science Foundation of Jiangsu Province under Grant No. BK20190089; Industrial Robot Application of Fujian University Engineering Research Center, Minjiang University under Grant No. MJUKF-IRA201806.

Author information

Authors and Affiliations

  1. Guangdong University of Petrochemical Technology, No. 139, Guandu 2 Road, Maoming, 525000, China

    Songsong Wu

  2. Institute of Advanced Technology, Nanjing University of Posts and Telecommunications, No. 9 Wenyuan Road, Nanjing, 210023, China

    Guangwei Gao

  3. Department of Computer Science, Minjiang University, No. 200 Zhenxiyuangong Road, Shangjie District, Minhou Town, Fuzhou, 350108, China

    Zuoyong Li

  4. School of Automation, Nanjing University of Posts and Telecommunications, No. 9 Wenyuan Road, Nanjing, 210023, China

    Fei Wu

  5. School of Computer Science, Wuhan University, No. 299, Bayi Road, Wuchang District, Wuhan, 430072, China

    Xiao-Yuan Jing

Authors
  1. Songsong Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guangwei Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zuoyong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fei Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiao-Yuan Jing
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Songsong Wu.

Ethics declarations

Conflict of interest

The authors declare that there is 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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, S., Gao, G., Li, Z. et al. Unsupervised visual domain adaptation via discriminative dictionary evolution. Pattern Anal Applic 23, 1665–1675 (2020). https://doi.org/10.1007/s10044-020-00881-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-020-00881-w

Keywords

Search

Navigation