Skip to main content
Springer Nature Link
Log in

Combating Label Distribution Shift for Active Domain Adaptation

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13693))

Included in the following conference series:

Abstract

We consider the problem of active domain adaptation (ADA) to unlabeled target data, of which subset is actively selected and labeled given a budget constraint. Inspired by recent analysis on a critical issue from label distribution mismatch between source and target in domain adaptation, we devise a method that addresses the issue for the first time in ADA. At its heart lies a novel sampling strategy, which seeks target data that best approximate the entire target distribution as well as being representative, diverse, and uncertain. The sampled target data are then used not only for supervised learning but also for matching label distributions of source and target domains, leading to remarkable performance improvement. On four public benchmarks, our method substantially outperforms existing methods in every adaptation scenario.

J. Ok and S. Kwak—Co-corresponding authors.

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

Notes

  1. 1.

    The domains are chosen considering their consistency with existing benchmarks [36].

  2. 2.

    Unfortunately, \(\text {S}^\text {3}\)VAADA [40] for DomainNet and VisDA-2017 requires infeasible memory consumption, in the supplementary material, we report its performance on a part of scenarios of DomainNet which our resource allows.

References

  1. Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M.: Domain-adversarial neural networks. arXiv preprint arXiv:1412.4446 (2014)

  2. Asghar, N., Poupart, P., Jiang, X., Li, H.: Deep active learning for dialogue generation. In: Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017) (2017)

    Google Scholar 

  3. Ash, J.T., Zhang, C., Krishnamurthy, A., Langford, J., Agarwal, A.: Deep batch active learning by diverse, uncertain gradient lower bounds. In: Proceedings of the International Conference on Learning Representations (ICLR) (2020)

    Google Scholar 

  4. 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), 151–175 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  5. Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)

    Google Scholar 

  6. Tachet des Combes, R., Zhao, H., Wang, Y.X., Gordon, G.J.: Domain adaptation with conditional distribution matching and generalized label shift. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2020)

    Google Scholar 

  7. Courty, N., Flamary, R., Habrard, A., Rakotomamonjy, A.: Joint distribution optimal transportation for domain adaptation. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2017)

    Google Scholar 

  8. Courty, N., Flamary, R., Tuia, D., Rakotomamonjy, A.: Optimal transport for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 39(9), 1853–1865 (2016)

    Article  Google Scholar 

  9. Cui, S., Wang, S., Zhuo, J., Su, C., Huang, Q., Tian, Q.: Gradually vanishing bridge for adversarial domain adaptation. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2020)

    Google Scholar 

  10. Dai, D., Sakaridis, C., Hecker, S., Van Gool, L.: Curriculum model adaptation with synthetic and real data for semantic foggy scene understanding. Int. J. Comput. Vis. (IJCV) 128, 1182–1204 (2020). https://doi.org/10.1007/s11263-019-01182-4

  11. Damodaran, B.B., Kellenberger, B., Flamary, R., Tuia, D., Courty, N.: DeepJDOT: deep joint distribution optimal transport for unsupervised domain adaptation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 467–483. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_28

    Chapter  Google Scholar 

  12. Deheeger, F., MOUGEOT, M., Vayatis, N., et al.: Discrepancy-based active learning for domain adaptation. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)

    Google Scholar 

  13. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2009)

    Google Scholar 

  14. Fu, B., Cao, Z., Wang, J., Long, M.: Transferable query selection for active domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)

    Google Scholar 

  15. Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. (JMLR) 17(1), 2096–2030 (2016)

    Google Scholar 

  16. Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  17. Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. (JMLR) 13(1), 723–773 (2012)

    MathSciNet  MATH  Google Scholar 

  18. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016)

    Google Scholar 

  19. He, T., Jin, X., Ding, G., Yi, L., Yan, C.: Towards better uncertainty sampling: active learning with multiple views for deep convolutional neural network. In: 2019 IEEE International Conference on Multimedia and Expo (ICME) (2019)

    Google Scholar 

  20. Huang, J.Z., Ng, M.K., Rong, H., Li, Z.: Automated variable weighting in k-means type clustering. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 27(5), 657–668 (2005)

    Article  Google Scholar 

  21. Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: Proceedings of the International Conference on Learning Representations (ICLR) (2020)

    Google Scholar 

  22. Kim, B., Khanna, R., Koyejo, O.O.: Examples are not enough, learn to criticize! Criticism for interpretability. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2016)

    Google Scholar 

  23. LeCun, Y., Chopra, S., Hadsell, R., Ranzato, M., Huang, F.: A tutorial on energy-based learning. Predict. Struct. Data 1(0) (2006)

    Google Scholar 

  24. 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 (CVPR) (2019)

    Google Scholar 

  25. Lee, S., Son, T., Kwak, S.: FIFO: learning fog-invariant features for foggy scene segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

    Google Scholar 

  26. Li, J., Li, G., Shi, Y., Yu, Y.: Cross-domain adaptive clustering for semi-supervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)

    Google Scholar 

  27. Li, K., Liu, C., Zhao, H., Zhang, Y., Fu, Y.: ECACL: a holistic framework for semi-supervised domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  28. Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: Proceedings of the International Conference on Machine Learning (ICML). PMLR (2015)

    Google Scholar 

  29. Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2018)

    Google Scholar 

  30. Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: Proceedings of the International Conference on Machine Learning (ICML). PMLR (2017)

    Google Scholar 

  31. Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. (JMLR) 9(11) (2008)

    Google Scholar 

  32. Nemhauser, G.L., Wolsey, L.A., Fisher, M.L.: An analysis of approximations for maximizing submodular set functions-I. Math. Program. 14(1), 265–294 (1978)

    Article  MathSciNet  MATH  Google Scholar 

  33. Ostapuk, N., Yang, J., Cudré-Mauroux, P.: Activelink: deep active learning for link prediction in knowledge graphs. In: The World Wide Web Conference (WWW) (2019)

    Google Scholar 

  34. Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  35. Peng, X., et al.: VisDA: a synthetic-to-real benchmark for visual domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2021–2026 (2018)

    Google Scholar 

  36. Prabhu, V., Chandrasekaran, A., Saenko, K., Hoffman, J.: Active domain adaptation via clustering uncertainty-weighted embeddings. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  37. Purushotham, S., Carvalho, W., Nilanon, T., Liu, Y.: Variational recurrent adversarial deep domain adaptation. In: Proceedings of the International Conference on Learning Representations (ICLR) (2016)

    Google Scholar 

  38. Qi, H., Brown, M., Lowe, D.G.: Low-shot learning with imprinted weights. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Google Scholar 

  39. Rai, P., Saha, A., Daumé III, H., Venkatasubramanian, S.: Domain adaptation meets active learning. In: Proceedings of the NAACL HLT 2010 Workshop on Active Learning for Natural Language Processing (2010)

    Google Scholar 

  40. Rangwani, H., Jain, A., Aithal, S.K., Babu, R.V.: S3VAADA: submodular subset selection for virtual adversarial active domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  41. Rdusseeun, L., Kaufman, P.: Clustering by means of medoids. In: Proceedings of the Statistical Data Analysis Based on the L1 Norm Conference, Neuchatel, Switzerland, vol. 31 (1987)

    Google Scholar 

  42. Roth, D., Small, K.: Margin-based active learning for structured output spaces. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 413–424. Springer, Heidelberg (2006). https://doi.org/10.1007/11871842_40

    Chapter  Google Scholar 

  43. Saito, K., Kim, D., Sclaroff, S., Darrell, T., Saenko, K.: Semi-supervised domain adaptation via minimax entropy. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  44. Sakaridis, C., Dai, D., Gool, L.V.: Guided curriculum model adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  45. Sakaridis, C., Dai, D., Hecker, S., Van Gool, L.: Model adaptation with synthetic and real data for semantic dense foggy scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 707–724. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_42

    Chapter  Google Scholar 

  46. Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vis. 126(9), 973–992 (2018). https://doi.org/10.1007/s11263-018-1072-8

    Article  Google Scholar 

  47. Sener, O., Savarese, S.: Active learning for convolutional neural networks: a core-set approach. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)

    Google Scholar 

  48. Settles, B.: Active learning literature survey (2009)

    Google Scholar 

  49. Seung, H.S., Opper, M., Sompolinsky, H.: Query by committee. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, pp. 287–294 (1992)

    Google Scholar 

  50. Shu, R., Bui, H.H., Narui, H., Ermon, S.: A DIRT-T approach to unsupervised domain adaptation. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)

    Google Scholar 

  51. Sinha, S., Ebrahimi, S., Darrell, T.: Variational adversarial active learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  52. Su, J.C., Tsai, Y.H., Sohn, K., Liu, B., Maji, S., Chandraker, M.: Active adversarial domain adaptation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (2020)

    Google Scholar 

  53. Tan, S., Peng, X., Saenko, K.: Class-imbalanced domain adaptation: an empirical Odyssey. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12535, pp. 585–602. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66415-2_38

    Chapter  Google Scholar 

  54. Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2015)

    Google Scholar 

  55. Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)

    Google Scholar 

  56. Wang, Z., Du, B., Tu, W., Zhang, L., Tao, D.: Incorporating distribution matching into uncertainty for multiple kernel active learning. IEEE Trans. Knowl. Data Eng. 33(1), 128–142 (2019)

    Article  Google Scholar 

  57. Wang, Z., Ye, J.: Querying discriminative and representative samples for batch mode active learning. ACM Trans. Knowl. Discov. Data (TKDD) 9(3), 1–23 (2015)

    Google Scholar 

  58. Xie, B., Yuan, L., Li, S., Liu, C.H., Cheng, X., Wang, G.: Active learning for domain adaptation: An energy-based approach. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2022)

    Google Scholar 

  59. Xie, M., et al.: Learning distinctive margin toward active domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

    Google Scholar 

  60. Xu, R., Li, G., Yang, J., Lin, L.: Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  61. Yang, L., et al.: Deep co-training with task decomposition for semi-supervised domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)

    Google Scholar 

  62. Yoon, J., Kang, D., Cho, M.: Semi-supervised domain adaptation via sample-to-sample self-distillation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1978–1987 (2022)

    Google Scholar 

  63. Zhao, H., Des Combes, R.T., Zhang, K., Gordon, G.: On learning invariant representations for domain adaptation. In: Proceedings of the International Conference on Machine Learning (ICML). PMLR (2019)

    Google Scholar 

Download references

Acknowledgements

This work was supported by the NRF grant and the IITP grant funded by Ministry of Science and ICT, Korea (NRF-2018R1A5-A1060031, NRF-2021R1A2C3012728, IITP-2019-0-01906, IITP-2020-0-00842, IITP-2021-0-02068, IITP-2022-0-00290).

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, POSTECH, Pohang, Korea

    Sehyun Hwang, Sungyeon Kim, Jungseul Ok & Suha Kwak

  2. Graduate School of Artificial Intelligence, Pohang, Korea

    Sohyun Lee, Jungseul Ok & Suha Kwak

Authors
  1. Sehyun Hwang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sohyun Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sungyeon Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jungseul Ok
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Suha Kwak
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Suha Kwak .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1760 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 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

Hwang, S., Lee, S., Kim, S., Ok, J., Kwak, S. (2022). Combating Label Distribution Shift for Active Domain Adaptation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13693. Springer, Cham. https://doi.org/10.1007/978-3-031-19827-4_32

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19827-4_32

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19826-7

  • Online ISBN: 978-3-031-19827-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics