Skip to main content
SpringerLink
Log in

Revisiting Unsupervised Domain Adaptation Models: A Smoothness Perspective

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13846))

Included in the following conference series:

Abstract

Unsupervised Domain Adaptation (UDA) aims to leverage the labeled source data and unlabeled target data to generalize better in the target domain. UDA methods utilize better domain alignment or carefully-designed regularizations to increase the discriminability of target features. However, most methods focus on directly increasing the distance between cluster centers of target features, i.e., enlarging inter-class variance, which intuitively increases the discriminability of target features and is easy to implement. However, due to intra-class variance optimization being under-explored, there are still some samples of the same class are prone to be classified into several classes. To handle this problem, we aim to equip UDA methods with the high smoothness constraint. We first define the model’s smoothness as the predictions similarity within each class, and propose a simple yet effective technique LeCo (impLicit smoothness Constraint) to promote the smoothness. We construct the weak and strong “views” of each target sample and enforce the model predictions of these two views to be consistent. Besides, a new uncertainty measure named Instance Class Confusion conditions the consistency is proposed to guarantee the transferability. LeCo implicitly reduces the model sensitivity to perturbations for target samples and guarantees smaller intra-class variance. Extensive experiments show that the proposed technique improves various baseline approaches by a large margin, and helps yield comparable results to the state-of-the-arts on four public datasets. Our codes are publicly available at https://github.com/Wang-Xiaodong1899/LeCo_UDA.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738 (2020)

    Google Scholar 

  2. Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9650–9660 (2021)

    Google Scholar 

  3. He, K., Chen, X., Xie, S., Li, Y., Dollár, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)

  4. Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: Visda: the visual domain adaptation challenge. arXiv preprint arXiv:1710.06924 (2017)

  5. Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: Advances in Neural Information Processing Systems, vol. 19 (2006)

    Google Scholar 

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

    Article  MathSciNet  MATH  Google Scholar 

  7. Zhao, S., et al.: A review of single-source deep unsupervised visual domain adaptation. IEEE Trans. Neural Netw. Learn. Syst. (2020)

    Google Scholar 

  8. Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Plann. Inference 90, 227–244 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  9. 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 

  10. Cui, S., Wang, S., Zhuo, J., Li, L., Huang, Q., Tian, Q.: Towards discriminability and diversity: batch nuclear-norm maximization under label insufficient situations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3941–3950 (2020)

    Google Scholar 

  11. 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, pp. 1426–1435 (2019)

    Google Scholar 

  12. Zhang, Y., Liu, T., Long, M., Jordan, M.: Bridging theory and algorithm for domain adaptation. In: International Conference on Machine Learning, pp. 7404–7413 (2019)

    Google Scholar 

  13. French, G., Mackiewicz, M., Fisher, M.H.: Self-ensembling for visual domain adaptation. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 April–3 May 2018, Conference Track Proceedings, OpenReview.net (2018)

    Google Scholar 

  14. Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, 3–8 December 2018, Montréal, Canada, vol. 31, pp. 1647–1657 (2018)

    Google Scholar 

  15. 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 

  16. Zhao, Y., Cai, L., et al.: Reducing the covariate shift by mirror samples in cross domain alignment. In: Advances in Neural Information Processing Systems, vol. 34 (2021)

    Google Scholar 

  17. Liang, J., Hu, D., Feng, J.: Domain adaptation with auxiliary target domain-oriented classifier. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16632–16642 (2021)

    Google Scholar 

  18. Sohn, K., et al.: Fixmatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, 6–12 December 2020, virtual, vol. 33 (2020)

    Google Scholar 

  19. Berthelot, D., Carlini, N., Goodfellow, I.J., Papernot, N., Oliver, A., Raffel, C.: Mixmatch: a holistic approach to semi-supervised learning. In: Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8–14 December 2019, Vancouver, BC, Canada, vol. 32, pp. 5050–5060 (2019)

    Google Scholar 

  20. Grandvalet, Y., Bengio, Y., et al.: Semi-supervised learning by entropy minimization. CAP 367, 281–296 (2005)

    Google Scholar 

  21. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014)

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

    Google Scholar 

  23. Ma, N., et al.: Context-guided entropy minimization for semi-supervised domain adaptation. Neural Netw. 154, 270–282 (2022)

    Article  Google Scholar 

  24. Yao, T., Pan, Y., Ngo, C.W., Li, H., Mei, T.: Semi-supervised domain adaptation with subspace learning for visual recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2142–2150 (2015)

    Google Scholar 

  25. 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, pp. 8050–8058 (2019)

    Google Scholar 

  26. Kim, T., Kim, C.: Attract, perturb, and explore: learning a feature alignment network for semi-supervised domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 591–607. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_35

    Chapter  Google Scholar 

  27. Li, R., Jiao, Q., Cao, W., Wong, H.S., Wu, S.: Model adaptation: unsupervised domain adaptation without source data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9641–9650 (2020)

    Google Scholar 

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

    Google Scholar 

  29. Wang, X., Zhuo, J., Cui, S., Wang, S.: Learning invariant representation with consistency and diversity for semi-supervised source hypothesis transfer. arXiv preprint arXiv:2107.03008 (2021)

  30. Shu, Y., Cao, Z., Long, M., Wang, J.: Transferable curriculum for weakly-supervised domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4951–4958 (2019)

    Google Scholar 

  31. Zhuo, J., Wang, S., Huang, Q.: Uncertainty modeling for robust domain adaptation under noisy environments. IEEE Trans. Multimedia (2022)

    Google Scholar 

  32. Zhuo, J., Wang, S., Zhang, W., Huang, Q.: Deep unsupervised convolutional domain adaptation. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 261–269. ACM (2017)

    Google Scholar 

  33. Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: International Conference on Machine Learning, pp. 2208–2217 (2017)

    Google Scholar 

  34. Zellinger, W., Grubinger, T., Lughofer, E., Natschläger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, Conference Track Proceedings, 24–26 April 2017. OpenReview.net (2017)

    Google Scholar 

  35. Borgwardt, K.M., Gretton, A., Rasch, M.J., Kriegel, H.P., Schölkopf, B., Smola, A.J.: Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics 22, e49–e57 (2006)

    Article  Google Scholar 

  36. Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)

    Google Scholar 

  37. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learning, pp. 1180–1189 (2015)

    Google Scholar 

  38. 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, pp. 3723–3732 (2018)

    Google Scholar 

  39. Li, S., Lv, F., Xie, B., Liu, C.H., Liang, J., Qin, C.: Bi-classifier determinacy maximization for unsupervised domain adaptation. In: AAAI, vol. 2, p. 5 (2021)

    Google Scholar 

  40. Cui, S., Wang, S., Zhuo, J., Li, L., Huang, Q., Tian, Q.: Fast batch nuclear-norm maximization and minimization for robust domain adaptation. arXiv preprint arXiv:2107.06154 (2021)

  41. Zhuo, J., Wang, S., Cui, S., Huang, Q.: Unsupervised open domain recognition by semantic discrepancy minimization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 750–759 (2019)

    Google Scholar 

  42. Li, S., Xie, B., Lin, Q., Liu, C.H., Huang, G., Wang, G.: Generalized domain conditioned adaptation network. IEEE Trans. Pattern Anal. Mach. Intell. (2021)

    Google Scholar 

  43. Li, S., Xie, M., Gong, K., Liu, C.H., Wang, Y., Li, W.: Transferable semantic augmentation for domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11516–11525 (2021)

    Google Scholar 

  44. Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, vol. 30 (2017)

    Google Scholar 

  45. Verma, V., Kawaguchi, K., Lamb, A., Kannala, J., Bengio, Y., Lopez-Paz, D.: Interpolation consistency training for semi-supervised learning. arXiv preprint arXiv:1903.03825 (2019)

  46. Chen, Y., Zhu, X., Gong, S.: Semi-supervised deep learning with memory. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 275–291. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01246-5_17

    Chapter  Google Scholar 

  47. Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April 2017, Conference Track Proceedings. OpenReview.net (2017)

    Google Scholar 

  48. Athiwaratkun, B., Finzi, M., Izmailov, P., Wilson, A.G.: There are many consistent explanations of unlabeled data: why you should average. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6–9 May 2019. OpenReview.net (2019)

    Google Scholar 

  49. Zhang, Y., Li, J., Wang, Z.: Low-confidence samples matter for domain adaptation. arXiv preprint arXiv:2202.02802 (2022)

  50. Zheng, Z., Yang, Y.: Unsupervised scene adaptation with memory regularization in vivo. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 1076–1082 (2021)

    Google Scholar 

  51. Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702–703 (2020)

    Google Scholar 

  52. 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_16

    Chapter  Google Scholar 

  53. 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 

  54. 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, pp. 1406–1415 (2019)

    Google Scholar 

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

  56. You, K., Wang, X., Long, M., Jordan, M.: Towards accurate model selection in deep unsupervised domain adaptation. In: International Conference on Machine Learning, pp. 7124–7133. PMLR (2019)

    Google Scholar 

  57. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  58. Tang, H., Chen, K., Jia, K.: Unsupervised domain adaptation via structurally regularized deep clustering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8725–8735 (2020)

    Google Scholar 

  59. Li, S., Lv, F., Xie, B., Liu, C.H., Liang, J., Qin, C.: Bi-classifier determinacy maximization for unsupervised domain adaptation. In: Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, 2–9 February 2021, pp. 8455–8464. AAAI Press (2021)

    Google Scholar 

  60. Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4893–4902 (2019)

    Google Scholar 

  61. Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167–7176 (2017)

    Google Scholar 

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

    Google Scholar 

Download references

Acknowledgement

The paper is supported in part by the National Key Research and Development Project (Grant No.2020AAA0106600), in part by National Natural Science Foundation of China: 62022083.

Author information

Authors and Affiliations

  1. School of Software and Microelectronics, Peking University, Beijing, China

    Xiaodong Wang & Yuejian Fang

  2. Key Laboratory of Intelligent Information Processing, Indian Institute of Computer Technology, CAS, Beijing, China

    Junbao Zhuo & Shuhui Wang

  3. MEGVII Technology, Beijing, China

    Mengru Zhang

Authors
  1. Xiaodong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Junbao Zhuo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mengru Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shuhui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuejian Fang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Junbao Zhuo or Yuejian Fang .

Editor information

Editors and Affiliations

  1. University of Wollongong, Wollongong, NSW, Australia

    Lei Wang

  2. University of Bonn, Bonn, Germany

    Juergen Gall

  3. University of Adelaide, Adelaide, SA, Australia

    Tat-Jun Chin

  4. National Institute of Informatics, Tokyo, Japan

    Imari Sato

  5. Johns Hopkins University, Baltimore, MD, USA

    Rama Chellappa

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 187 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2023 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

Wang, X., Zhuo, J., Zhang, M., Wang, S., Fang, Y. (2023). Revisiting Unsupervised Domain Adaptation Models: A Smoothness Perspective. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds) Computer Vision – ACCV 2022. ACCV 2022. Lecture Notes in Computer Science, vol 13846. Springer, Cham. https://doi.org/10.1007/978-3-031-26351-4_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-26351-4_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-26350-7

  • Online ISBN: 978-3-031-26351-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation