Skip to main content
SpringerLink
Log in

A source free domain adaptation model based on adversarial learning for image classification

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The unsupervised domain adaptive classification task can learn domain-invariant features between the unlabeled target domain and the labeled source domain, thereby improving the classification performance in target domain. However, privacy protection and memory constrains often make it difficult to obtain labeled source domain samples, which become bottlenecks for the traditional domain adaptation. To this end, we propose a novel source free domain adaptive classification model. This model helps us to obtain a classifier with better effect in the target domain only by using the classifier trained in source domain and the target domain data without any source domain data. Firstly we propose a novel conditional information generative adversarial module based on combined discriminators. By confronting between combined discriminators and the generator, the middle domain with pseudo-labels is generated to solve the problem of missing source domain. Then when training the new classifier in domain adaptation module, we add a distillation loss mechanism to deal with the lack of source domain data supervision, thereby minimizing the difference between the old classifier response and the new classifier response to ensure that the network output retains the source domain information. Three groups of 10 datasets are used to verify this models. The results show that our methods can effectively solve the problem of source free domain adaptive classification and improve the classification accuracy in each domain.

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
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105

    Google Scholar 

  2. Simonyan K, Zisserman A (2014)

  3. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  4. Gholenji E, Tahmoresnezhad J (2020) Joint discriminative subspace and distribution adaptation for unsupervised domain adaptation. Appl Intell 50(7):2050–2066

    Article  Google Scholar 

  5. Yang G, Ding M, Zhang Y (2021) Bi-directional class-wise adversaries for unsupervised domain adaptation. Appl Intell 52:3623–3639

    Article  Google Scholar 

  6. Long M, Cao Y, Wang J, Jordan M (2015) Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, PMLR, pp 97–105

  7. Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014)

  8. Zellinger W, Grubinger T, Lughofer E, Natschläger T, Saminger-Platz S (2017)

  9. Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International conference on machine learning, PMLR, pp 1180–1189

  10. Pei Z, Cao Z, Long M, Wang J (2018) Multi-adversarial domain adaptation. In: Thirty-second AAAI conference on artificial intelligence

  11. Saito K, Watanabe K, Ushiku Y, Harada T (2018) Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3723–3732

  12. Wang H, Shen T, Zhang W, Duan L-Y, Mei T (2020) Classes matter: A fine-grained adversarial approach to cross-domain semantic segmentation. In: European conference on computer vision, Springer, pp 642–659

  13. Wang S, Zhang L (2020) Self-adaptive re-weighted adversarial domain adaptation. arXiv:2006.00223

  14. Chen C, Chen Z, Jiang B, Jin X (2019) Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 33. pp 3296–3303

  15. Sun B, Feng J, Saenko K (2016) Return of frustratingly easy domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 30.

  16. Sun B, Saenko K (2016) Deep coral: Correlation alignment for deep domain adaptation. In: European conference on computer vision, Springer, pp 443–450

  17. Zhuo J, Wang S, Zhang W, Huang Q (2017) Deep unsupervised convolutional domain adaptation. In: Proceedings of the 25th ACM international conference on multimedia, pp 261– 269

  18. Pinheiro PO (2018) Unsupervised domain adaptation with similarity learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8004–8013

  19. Lee C-Y, Batra T, Baig MH, Ulbricht D (2019) Sliced wasserstein discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10285–10295

  20. Kurmi VK, Bajaj V, Subramanian VK, Namboodiri VP (2019) Curriculum based dropout discriminator for domain adaptation. arXiv:1907

  21. Radford A, Metz L, Chintala S (2015)

  22. Mirza M, Osindero S (2014)

  23. Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232

  24. Donahue J, Krähenbühl P, Darrell T (2016)

  25. Donahue J, Simonyan K (2019) Large scale adversarial representation learning. Adv Neural Inf Process Syst 32:10542–10552

    Google Scholar 

  26. Li R, Jiao Q, Cao W, Wong H-S, Wu S (2020) Model adaptation: unsupervised domain adaptation without source data. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 9641–9650

  27. Kurmi VK, Subramanian VK, Namboodiri VP (2021) Domain impression: a source data free domain adaptation method. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp 615–625

  28. Liang J, Hu D, Feng J (2020) Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In: International conference on machine learning, PMLR, pp 6028–6039

  29. Hou Y, Zheng L (2021) Visualizing adapted knowledge in domain transfer. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 13824–13833

  30. Lim JH, Ye JC (2017) Geometric gan. arXiv:1705.02894

  31. Tran D, Ranganath R, Blei DM (2017) Hierarchical implicit models and likelihood-free variational inference. Adv Neural Inf Process Syst 2017:5524–5534

    Google Scholar 

  32. Brock A, Donahue J, Simonyan K (2018) Large scale gan training for high fidelity natural image synthesis. In: International conference on learning representations

  33. Miyato T, Kataoka T, Koyama M, Yoshida Y (2018) Spectral normalization for generative adversarial networks. arXiv:1802.05957

  34. Shmelkov K, Schmid C, Alahari K (2017) Incremental learning of object detectors without catastrophic forgetting. In: Proceedings of the IEEE international conference on computer vision, pp 3400–3409

  35. LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11):2278–2324

    Article  Google Scholar 

  36. Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res 17(1):2096–2030

    MathSciNet  MATH  Google Scholar 

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

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

    Article  Google Scholar 

  39. Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: European conference on computer vision, Springer, pp 213–226

  40. Ghifary M, Kleijn WB, Zhang M, Balduzzi D, Li W (2016) Deep reconstruction-classification networks for unsupervised domain adaptation. In: European conference on computer vision, Springer, pp 597–613

  41. Saito K, Ushiku Y, Harada T (2017) Asymmetric tri-training for unsupervised domain adaptation. In: International conference on machine learning, PMLR, pp 2988–2997

  42. Cicek S, Soatto S (2019) Unsupervised domain adaptation via regularized conditional alignment. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1416–1425

  43. Sankaranarayanan S, Balaji Y, Castillo CD, Chellappa R (2018) Generate to adapt: aligning domains using generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8503–8512

  44. Tang H, Jia K (2020) Discriminative adversarial domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 34. pp 5940–5947

  45. Long M, Zhu H, Wang J, Jordan MI (2016) Unsupervised domain adaptation with residual transfer networks. Adv Neural Inf Process Syst 29:136–144

    Google Scholar 

  46. Long M, Zhu H, Wang J, Jordan MI (2017) Deep transfer learning with joint adaptation networks. In: International conference on machine learning, PMLR, pp 2208–2217

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

    Article  MathSciNet  MATH  Google Scholar 

  48. Shen J, Qu Y, Zhang W, Yu Y (2018) Wasserstein distance guided representation learning for domain adaptation. In: Thirty-second AAAI conference on artificial intelligence

Download references

Acknowledgments

This work was supported by Joint Fund of Natural Science Foundation of Anhui Province in 2020 (2008085UD08), Anhui Provincial Key R&D Program (201904d08020008, 202004a05020004) and Intelligent Networking and New Energy Vehicle Special Project of Intelligent Manufacturing Institute of HFUT (IMIWL2019003, IMIDC2019002). In addition, it was also supported by the Fundamental Research Funds for the Central Universities(JZ2021HGQA0199), and the nurturing project for Science and Technology achievements aided by Intelligent Manufacturing Institute of HFUT(IMIPY2021020).

Author information

Author notes

    Authors and Affiliations

    1. School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China

      Yujie Liu, Yang Lu & Wei Xing

    2. Engineering Quality Education Center of Undergraduate School, Hefei University of Technology, Hefei, China

      Chong Zhao

    3. Intelligent Manufacturing Institute, Hefei University of Technology, Hefei, China

      Chong Zhao & Wei Xing

    4. Engineering Research Center of Safety Critical Industrial Measurement and Control Technology, Ministry of Education, Hefei, 230009, China

      Wei Xing

    5. School of Informatics, The University of Edinburgh, Edinburgh, UK

      Xuanyuan Qiao

    Authors
    1. Yujie Liu
      View author publications

      You can also search for this author in PubMed Google Scholar

    2. Chong Zhao
      View author publications

      You can also search for this author in PubMed Google Scholar

    3. Yang Lu
      View author publications

      You can also search for this author in PubMed Google Scholar

    4. Wei Xing
      View author publications

      You can also search for this author in PubMed Google Scholar

    5. Xuanyuan Qiao
      View author publications

      You can also search for this author in PubMed Google Scholar

    Corresponding author

    Correspondence to Chong Zhao.

    Additional information

    Publisher’s note

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

    Chong Zhao, Yang Lu, Wei Xing and Xuanyuan Qiao are contributed equally to this work.

    Rights and permissions

    Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

    Reprints and permissions

    About this article

    Check for updates. Verify currency and authenticity via CrossMark

    Cite this article

    Liu, Y., Zhao, C., Lu, Y. et al. A source free domain adaptation model based on adversarial learning for image classification. Appl Intell 53, 11389–11402 (2023). https://doi.org/10.1007/s10489-022-04026-w

    Download citation

    • Accepted:

    • Published:

    • Issue Date:

    • DOI: https://doi.org/10.1007/s10489-022-04026-w

    Keywords

    Search

    Navigation