Skip to main content
SpringerLink
Log in

Enhancing unsupervised domain adaptation by exploiting the conceptual consistency of multiple self-supervised tasks

  • Research Paper
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

Unsupervised domain adaptation (UDA) aims to transfer the knowledge from a label-rich source domain to an unlabeled target domain. Current approaches mainly focus on aligning the target domain’s data distribution with the source domain, but lacking attention to allowing target data to guide which features need to be captured. Source data dominates feature extraction. As a result, target embedding would lose some vital discriminative features and limit UDA in complex tasks. In this paper, we argue that utilizing auxiliary tasks to capture target-intrinsic patterns, which do not depend on source supervision, could further enhance UDA. Multiple auxiliary tasks understand the instance concept from different perspectives. Our findings show that exploiting the conceptual consistency of multiple auxiliary tasks to characterize the common part of these various understandings should reveal the target’s hidden ground truth. Furthermore, we propose a novel method named multiple self-supervision conceptual consistency domain adaptation (MSCC). Experiments and analysis on benchmark datasets show the effectiveness of our idea and method.

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

Similar content being viewed by others

References

  1. Pan S J, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng, 2009, 22: 1345–1359

    Article  Google Scholar 

  2. Dai W Y, Yang Q. Xue G R, et al. Boosting for transfer learning. In: Proceedings of the 24th International Conference on Machine Learning (ICML), 2007. 193–200

  3. Raina R, Battle A, Lee H, et al. Self-taught learning: transfer learning from unlabeled data. In: Proceedings of the 24th International Conference on Machine Learning (ICML), 2007. 759–766

  4. Lawrence N D, Platt J C. Learning to learn with the informative vector machine. In: Proceedings of the 21st International Conference on Machine Learning (ICML), 2004. 65

  5. Mihalkova L, Huynh T, Mooney R J. Mapping and revising Markov logic networks for transfer learning. In: Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI), 2007. 7: 608–614

    Google Scholar 

  6. Tzeng E, Hoffman J, Zhang N, et al. Deep domain confusion: maximizing for domain invariance. 2014. ArXiv:1412.3474

  7. Long M S, Cao Y, Wang J M, et al. Learning transferable features with deep adaptation networks. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015. 97–105

  8. Long M S, Zhu H, Wang J M, et al. Unsupervised domain adaptation with residual transfer networks. In: Proceedings of the Advances in Neural Information Processing Systems 29 (NeurIPS), 2016. 136–144

  9. Yaroslav G, Evgeniya U, Hana A, et al. Domain-adversarial training of neural networks. J Mach Learning Res, 2016, 17: 1–35

    MathSciNet  MATH  Google Scholar 

  10. Yaroslav G, Victor L. Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015. 1180–1189

  11. Tzeng E, Hoffman J, Saenko K, et al. Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. 7167–7176

  12. Chen C Q, Xie W P, Wen Y, et al. Multiple-source domain adaptation with generative adversarial nets. Knowledge-Based Syst, 2020, 199: 105962

    Article  Google Scholar 

  13. Judy H, Eric T, Taesung P, et al. CYCADA: cycle-consistent adversarial domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning (ICML), 2018. 1994–2003

  14. Wang Z M, Du B, Tu W P, et al. Incorporating distribution matching into uncertainty for multiple kernel active learning. IEEE Trans Knowl Data Eng, 2019, 33: 128–142

    Article  Google Scholar 

  15. Xie S A, Zheng Z B, Chen L, et al. Learning semantic representations for unsupervised domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning (ICML), 2018. 5423–5432

  16. Long M S, Cao Z J, Wang J M, et al. Conditional adversarial domain adaptation. In: Proceedings of the Advances in Neural Information Processing Systems 31 (NeurIPS), 2018. 1647–1657

  17. Pei Z Y, Cao Z J, Long M S, et al. Multi-adversarial domain adaptation. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018. 3934–3941

  18. Wang J D, Feng W J, Chen Y Q, et al. Visual domain adaptation with manifold embedded distribution alignment. In: Proceedings of the 26th ACM International Conference on Multimedia (MM), 2018. 402–410

  19. Wang Z M, Du B, Guo Y H. Domain adaptation with neural embedding matching. IEEE Trans Neural Netw Learn Syst, 2020, 31: 2387–2397

    Article  MathSciNet  Google Scholar 

  20. Saito K, Ushiku Y, Harada T, et al. Adversarial dropout regularization. In: Proceedings of the 6th International Conference on Learning Representations (ICLR), 2018

  21. Saito K, Watanabe K, Ushiku Y, et al. Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. 3723–3732

  22. Ghifary M, Kleijn W B, Zhang M, et al. Deep reconstruction-classification networks for unsupervised domain adaptation. In: Proceedings of the 14th European Conference on Computer Vision (ECCV), 2016. 597–613

  23. Sun Y, Tzeng E, Darrell T, et al. Unsupervised domain adaptation through self-supervision. 2019. ArXiv:1909.11825

  24. Zhou Z-H, Zhan D-C, Yang Q. Semi-supervised learning with very few labeled training examples. In: Proceedings of the 22nd AAAI Conference on Artificial Intelligence, 2007. 675–680

  25. Ben-David S, Blitzer J, Crammer K, et al. A theory of learning from different domains. Mach Learn, 2010, 79: 151–175

    Article  MathSciNet  MATH  Google Scholar 

  26. Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. 2014. ArXiv:1406.2661

  27. Gidaris S, Bursuc A, Komodakis N, et al. Boosting few-shot visual learning with self-supervision. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019. 8059–8068

  28. Lee H, Hwang S J, Shin J. Self-supervised label augmentation via input transformations. In: Proceedings of the 37th International Conference on Machine Learning (ICML), 2020. 5714–5724

  29. Kolesnikov A, Zhai X, Beyer L. Revisiting self-supervised visual representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. 1920–1929

  30. Jing L L, Tian Y L. Self-supervised visual feature learning with deep neural networks: a survey. IEEE Trans Pattern Anal Mach Intell, 2020, 43: 4037–4058

    Article  Google Scholar 

  31. Doersch C, Zisserman A. Multi-task self-supervised visual learning. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. 2070–2079

  32. Kalogeiton V, Weinzaepfel P, Ferrari V, et al. Joint learning of object and action detectors. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017. 4163–4172

  33. Tarvainen A, Valpola H. Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Proceedings of the Advances in Neural Information Processing Systems 30 (NeurIPS), 2017. 1195–1204

  34. Zou Y, Yu Z D, Liu X F, et al. Confidence regularized self-training. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2019. 5982–5991

  35. Wang Q, Breckon T P. Unsupervised domain adaptation via structured prediction based selective pseudo-labeling. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020. 34: 6243–6250

  36. Long M S, Zhu H, Wang J M, et al. Deep transfer learning with joint adaptation networks. In: Proceedings of the 34th International Conference on Machine Learning (ICML), 2017. 2208–2217

  37. Zhang H Y, Cisse M, Dauphin Y N, et al. MixUp: beyond empirical risk minimization. In: Proceedings of the 6th International Conference on Learning Representations (ICLR), 2018

  38. Berthelot D, Carlini N, Goodfellow I, et al. MixMatch: a holistic approach to semi-supervised learning. In: Proceedings of the Advances in Neural Information Processing Systems 32 (NeurIPS), 2019. 5049–5059

  39. Jiang J G, Fu B, Long M S. Transfer-learning-library. 2020. https://github.com/thuml/Transfer-Learning-Library

  40. He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 770–778

  41. Na J, Jung H, Chang H J, et al. FixBi: bridging domain spaces for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021. 1094–1103

  42. Laine S, Aila T. Temporal ensembling for semi-supervised learning. In: Proceedings of the 5th International Conference on Learning Representations (ICLR), 2015. 1–13

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (Grant Nos. 62076121, 61921006).

Author information

Authors and Affiliations

  1. National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210023, China

    Hui Sun & Ming Li

Authors
  1. Hui Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ming Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ming Li.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sun, H., Li, M. Enhancing unsupervised domain adaptation by exploiting the conceptual consistency of multiple self-supervised tasks. Sci. China Inf. Sci. 66, 142101 (2023). https://doi.org/10.1007/s11432-021-3535-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11432-021-3535-2

Keywords

Search

Navigation