Advertisement

Research on Distribution Alignment and Semantic Consistency in the Adversarial Domain Adaptation

  • Jingcheng Ni
  • Haiyang Jia
  • Fangyuan Zhang
  • Yixuan Wang
  • Juan Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11062)

Abstract

Domain adaptation is an effective method solving the learning tasks lack of labeled data. In recent years, the adversarial domain adaptation (ADA) has achieved attractive results in a series transfer learning tasks. ADA reduces the distribution discrepancy between the source and the target by extracting the domain invariant features. However, the lack of constraints on the transferable features leads to poor results even negative transfers. A novel ADA method is proposed to solve this problem which contains two main improvements: the conditional distribution alignment and the semantic consistency regularization. The experiment demonstrate that the proposed method has promising improvement in the classification accuracy on the benchmark dataset. The code and data can be downloaded from https://github.com/kiradiso/EADA.

Keywords

Domain adaptation Computer vision Generative adversarial network 

Notes

Acknowledgement

This paper is supported by National Natural Science Foundation of China under Grant Nos. 61502198, 61472161, 61402195, 61103091 and the Science and Technology Development Plan of Jilin Province under Grant No. 20160520099JH, 20150101051JC.

References

  1. 1.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  2. 2.
    Patel, V.M., et al.: Visual domain adaptation: a survey of recent advances. IEEE Sig. Process. Mag. 32(3), 53–69 (2015)CrossRefGoogle Scholar
  3. 3.
    Gong, B., Grauman, K., Sha, F.: Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In: International Conference on Machine Learning JMLR.org, p. I-222 (2013)Google Scholar
  4. 4.
    Pan, S.J., et al.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199–210 (2011)CrossRefGoogle Scholar
  5. 5.
    Nguyen, H.V., et al.: DASH-N: joint hierarchical domain adaptation and feature learning. IEEE Trans. Image Process. 24(12), 5479–5491 (2015)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Goodfellow, I.J., et al.: Generative adversarial networks. Adv. Neural Inf. Process. Syst. 3, 2672–2680 (2014)Google Scholar
  7. 7.
    Yosinski, J., et al.: How transferable are features in deep neural networks? vol. 27, pp. 3320–3328 (2014)Google Scholar
  8. 8.
    Tzeng, E., et al.: Deep domain confusion: maximizing for domain invariance. Comput. Sci. (2014). https://arxiv.org/abs/1412.3474
  9. 9.
    Zhang, L., Liu, Y., Deng, P.: Odor recognition in multiple E-nose systems with cross-domain discriminative subspace learning. IEEE Trans. Instrum. Measur. PP(99), 1–14 (2017)Google Scholar
  10. 10.
    Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation, pp. 1180–1189 (2014)Google Scholar
  11. 11.
    Wang, M., Deng, W.: Deep visual domain adaptation: a survey (2018)Google Scholar
  12. 12.
    Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plann. Inference 90(2), 227–244 (2000)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Busto, P.P., Gall, J.: Open set domain adaptation. In: IEEE International Conference on Computer Vision IEEE Computer Society, pp. 754–763 (2017)Google Scholar
  14. 14.
    Long, M., et al.: Transfer feature learning with joint distribution adaptation. In: IEEE International Conference on Computer Vision IEEE, pp. 2200–2207 (2014)Google Scholar
  15. 15.
    Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Comput. Sci. 14(7), 38–39 (2015)Google Scholar
  16. 16.
    Luo, Z., et al.: Label efficient learning of transferable representations across domains and tasks (2017)Google Scholar
  17. 17.
    Long, M., et al.: Learning transferable features with deep adaptation networks, pp. 97–105 (2015)Google Scholar
  18. 18.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15561-1_16CrossRefGoogle Scholar
  19. 19.
    Long, M., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Jingcheng Ni
    • 2
  • Haiyang Jia
    • 1
    • 2
    • 3
  • Fangyuan Zhang
    • 2
  • Yixuan Wang
    • 2
  • Juan Chen
    • 1
    • 2
    • 3
  1. 1.College of Computer Science and TechnologyJilin UniversityChangchunPeople’s Republic of China
  2. 2.College of SoftwareJilin UniversityChangchunPeople’s Republic of China
  3. 3.Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchunPeople’s Republic of China

Personalised recommendations