Skip to main content
Springer Nature Link
Log in

Improving Unsupervised Domain Adaptation: A Pseudo-candidate Set Approach

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15090))

Included in the following conference series:

  • 299 Accesses

Abstract

Unsupervised domain adaptation (UDA) is a critical challenge in machine learning, aiming to transfer knowledge from a labeled source domain to an unlabeled target domain. In this work, we aim to improve target set accuracy in any existing UDA method by introducing an approach that utilizes pseudo-candidate sets for labeling the target data. These pseudo-candidate sets serve as a proxy for the true labels in the absence of direct supervision. To enhance the accuracy of the target domain, we propose Unsupervised Domain Adaptation refinement using Pseudo-Candidate Sets (UDPCS), a method which effectively learns to disambiguate among classes in the pseudo-candidate set. Our approach is characterized by two distinct loss functions: one that acts on the pseudo-candidate set to refine its predictions and another that operates on the labels outside the pseudo-candidate set. We use a threshold-based strategy to further guide the learning process toward accurate label disambiguation. We validate our novel yet simple approach through extensive experiments on three well-known benchmark datasets: Office-Home, VisDA, and DomainNet. Our experimental results demonstrate the efficacy of our method in achieving consistent gains on target accuracies across these datasets.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

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

    Article  MathSciNet  Google Scholar 

  2. Chen, C., et al.: Homm: higher-order moment matching for unsupervised domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3422–3429 (2020)

    Google Scholar 

  3. Chen, L., et al.: Reusing the task-specific classifier as a discriminator: discriminator-free adversarial domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7181–7190 (2022)

    Google Scholar 

  4. Chen, W., Lin, L., Yang, S., Xie, D., Pu, S., Zhuang, Y.: Self-supervised noisy label learning for source-free unsupervised domain adaptation. In: 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10185–10192. IEEE (2022)

    Google Scholar 

  5. Chen, Y., Wei, C., Kumar, A., Ma, T.: Self-training avoids using spurious features under domain shift. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21061–21071 (2020)

    Google Scholar 

  6. Csurka, G.: Domain Adaptation for Visual Applications: A Comprehensive Survey, pp. 1–35. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58347-1

  7. Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space (2019)

    Google Scholar 

  8. DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout (2017)

    Google Scholar 

  9. Du, Z., Li, J., Su, H., Zhu, L., Lu, K.: Cross-domain gradient discrepancy minimization for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3937–3946 (2021)

    Google Scholar 

  10. Feng, L., et al.: Provably consistent partial-label learning. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 10948–10960. Curran Associates, Inc. (2020). https://proceedings.neurips.cc/paper_files/paper/2020/file/7bd28f15a49d5e5848d6ec70e584e625-Paper.pdf

  11. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd International Conference on Machine Learning (ICML) (2015)

    Google Scholar 

  12. Gao, Z., Zhang, S., Huang, K., Wang, Q., Zhong, C.: Gradient distribution alignment certificates better adversarial domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8937–8946 (2021)

    Google Scholar 

  13. Jiang, J., Chen, B., Fu, B., Long, M.: Transfer-learning-library (2020). https://github.com/thuml/Transfer-Learning-Library

  14. Jin, X., Lan, C., Zeng, W., Chen, Z.: Re-energizing domain discriminator with sample relabeling for adversarial domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9174–9183 (2021)

    Google Scholar 

  15. Jin, Y., Wang, X., Long, M., Wang, J.: Minimum class confusion for versatile domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 464–480. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_28

    Chapter  Google Scholar 

  16. Jing, X., Qian, K., Jianu, T., Luo, S.: Unsupervised adversarial domain adaptation for sim-to-real transfer of tactile images. IEEE Trans. Instrum. Meas. 72, 1–11 (2023). https://doi.org/10.1109/TIM.2023.3268458

    Article  Google Scholar 

  17. Kamilaris, A., Prenafeta-Boldú, F.X.: Deep learning in agriculture: a survey. Comput. Electron. Agric. 147, 70–90 (2018)

    Article  Google Scholar 

  18. Le, T., Nguyen, T., Ho, N., Bui, H., Phung, D.: Lamda: label matching deep domain adaptation. In: International Conference on Machine Learning, pp. 6043–6054. PMLR (2021)

    Google Scholar 

  19. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)

    Article  Google Scholar 

  20. Lee, C.Y., Batra, T., Baig, M.H., Ulbricht, D.: Sliced Wasserstein discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10285–10295 (2019)

    Google Scholar 

  21. Li, S., et al.: Domain conditioned adaptation network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 11386–11393 (2020)

    Google Scholar 

  22. Liu, H., Wang, J., Long, M.: Cycle self-training for domain adaptation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 22968–22981 (2021)

    Google Scholar 

  23. Liu, X., et al.: Adversarial unsupervised domain adaptation with conditional and label shift: infer, align and iterate. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 10367–10376 (2021)

    Google Scholar 

  24. Liu, Y., Zhou, Z., Sun, B.: Cot: Unsupervised domain adaptation with clustering and optimal transport. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 19998–20007 (2023)

    Google Scholar 

  25. Lv, J., Xu, M., Feng, L., Niu, G., Geng, X., Sugiyama, M.: Progressive identification of true labels for partial-label learning. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 6500–6510. PMLR, 13–18 July 2020. https://proceedings.mlr.press/v119/lv20a.html

  26. Mei, K., Zhu, C., Zou, J., Zhang, S.: Instance adaptive self-training for unsupervised domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 415–430. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58574-7_25

    Chapter  Google Scholar 

  27. Na, J., Jung, H., Chang, H.J., Hwang, W.: Fixbi: bridging domain spaces for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1094–1103 (2021)

    Google Scholar 

  28. Nguyen, T., Le, T., Dam, N., Tran, Q.H., Nguyen, T., Phung, D.Q.: Tidot: a teacher imitation learning approach for domain adaptation with optimal transport. In: IJCAI, pp. 2862–2868 (2021)

    Google Scholar 

  29. Patel, V.M., Gopalan, R., Li, R., Chellappa, R.: Visual domain adaptation: a survey of recent advances. IEEE Sig. Process. Mag. 32(3), 53–69 (2015)

    Article  Google Scholar 

  30. Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1406–1415 (2019)

    Google Scholar 

  31. Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: Visda: the visual domain adaptation challenge (2017)

    Google Scholar 

  32. Phan, H., Le, T., Phung, T., Bui, A.T., Ho, N., Phung, D.: Global-local regularization via distributional robustness. In: International Conference on Artificial Intelligence and Statistics, pp. 7644–7664. PMLR (2023)

    Google Scholar 

  33. Prabhu, V., Khare, S., Kartik, D., Hoffman, J.: Sentry: selective entropy optimization via committee consistency for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 8558–8567 (2021)

    Google Scholar 

  34. Qian, N.: On the momentum term in gradient descent learning algorithms. Neural Netw. 12(1), 145–151 (1999)

    Article  Google Scholar 

  35. Rangwani, H., Aithal, S.K., Mishra, M., Jain, A., Radhakrishnan, V.B.: A closer look at smoothness in domain adversarial training. In: International Conference on Machine Learning, pp. 18378–18399. PMLR (2022)

    Google Scholar 

  36. Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  37. Shen, D., Wu, G., Suk, H.I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017)

    Article  Google Scholar 

  38. Shin, I., Woo, S., Pan, F., Kweon, I.S.: Two-phase pseudo label densification for self-training based domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 532–548. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58601-0_32

    Chapter  Google Scholar 

  39. Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 596–608. Curran Associates, Inc. (2020). https://proceedings.neurips.cc/paper_files/paper/2020/file/06964dce9addb1c5cb5d6e3d9838f733-Paper.pdf

  40. Tian, Y., Yu, X., Fu, S.: Partial label learning: taxonomy, analysis and outlook. Neural Netw. 161, 708–734 (2023). https://doi.org/10.1016/j.neunet.2023.02.019, https://www.sciencedirect.com/science/article/pii/S0893608023000825

  41. Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  42. Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5018–5027 (2017)

    Google Scholar 

  43. Wang, X., Zhuo, J., Zhang, M., Wang, S., Fang, Y.: Revisiting unsupervised domain adaptation models: a smoothness perspective. In: Proceedings of the Asian Conference on Computer Vision, pp. 1504–1521 (2022)

    Google Scholar 

  44. Wei, G., Lan, C., Zeng, W., Chen, Z.: MetaAlign: coordinating domain alignment and classification for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16643–16653 (2021)

    Google Scholar 

  45. Wei, G., Lan, C., Zeng, W., Zhang, Z., Chen, Z.: ToAlign: task-oriented alignment for unsupervised domain adaptation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 13834–13846 (2021)

    Google Scholar 

  46. Wen, H., Cui, J., Hang, H., Liu, J., Wang, Y., Lin, Z.: Leveraged weighted loss for partial label learning. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 11091–11100. PMLR, 18–24 July 2021. https://proceedings.mlr.press/v139/wen21a.html

  47. Wu, D.D., Wang, D.B., Zhang, M.L.: Revisiting consistency regularization for deep partial label learning. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, pp. 24212–24225. PMLR, 17–23 July 2022. https://proceedings.mlr.press/v162/wu22l.html

  48. Xie, X., Chen, J., Li, Y., Shen, L., Ma, K., Zheng, Y.: Self-supervised CycleGAN for object-preserving image-to-image domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 498–513. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_30

    Chapter  Google Scholar 

  49. Yan, Y., Guo, Y.: Partial label unsupervised domain adaptation with class-prototype alignment. In: The Eleventh International Conference on Learning Representations (2022)

    Google Scholar 

  50. Zhang, Y., Liu, T., Long, M., Jordan, M.: Bridging theory and algorithm for domain adaptation. In: Proceedings of the 36th International Conference on Machine Learning (ICML) (2019)

    Google Scholar 

  51. Zhou, L., Ye, M., Zhu, X., Xiao, S., Fan, X.Q., Neri, F.: Homeomorphism alignment for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 18699–18710 (2023)

    Google Scholar 

Download references

Acknowledgements

The research of AD is supported in part by the Prime Minister Research Fellowship, Ministry of Education, Government of India. VNB would like to acknowledge the support through the Govt of India SERB IMPRINT and DST ICPS funding programs for this work. The research of CKM is supported by the LiDAR and Camera Sensors Data based Deep Learning Algorithms for Autonomous Driving System project, funded by Govt. of India SERB program. The research is also partly supported by the Indo-Norwegian Collaboration in Autonomous Cyber-Physical Systems (INCAPS) project: 287918 of the International Partnerships for Excellent Education, Research and Innovation (INTPART) program and the Low-Altitude UAV Communication and Tracking (LUCAT) project: 280835 of the IKTPLUSS program from the Research Council of Norway. We are grateful to the anonymous reviewers for the feedback that helped improved the presentation of this paper.

Author information

Authors and Affiliations

  1. Indian Institute of Technology Hyderabad, Hyderabad, 502285, India

    Aveen Dayal, Rishabh Lalla, C. Krishna Mohan, Abhinav Kumar & Vineeth N. Balasubramanian

  2. University of Agder, 4879, Grimstad, Norway

    Linga Reddy Cenkeramaddi

Authors
  1. Aveen Dayal
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rishabh Lalla
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Linga Reddy Cenkeramaddi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. C. Krishna Mohan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Abhinav Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Vineeth N. Balasubramanian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Aveen Dayal .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 3019 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Dayal, A., Lalla, R., Cenkeramaddi, L.R., Mohan, C.K., Kumar, A., Balasubramanian, V.N. (2025). Improving Unsupervised Domain Adaptation: A Pseudo-candidate Set Approach. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15090. Springer, Cham. https://doi.org/10.1007/978-3-031-73411-3_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-73411-3_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-73410-6

  • Online ISBN: 978-3-031-73411-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics