SpringerLink
Log in

Adversarial Partial Domain Adaptation by Cycle Inconsistency

  • 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

Unsupervised partial domain adaptation (PDA) is a unsupervised domain adaptation problem which assumes that the source label space subsumes the target label space. A critical challenge of PDA is the negative transfer problem, which is triggered by learning to match the whole source and target domains. To mitigate negative transfer, we note a fact that, it is impossible for a source sample of outlier classes to find a target sample of the same category due to the absence of outlier classes in the target domain, while it is possible for a source sample of shared classes. Inspired by this fact, we exploit the cycle inconsistency, i.e., category discrepancy between the original features and features after cycle transformations, to distinguish outlier classes apart from shared classes in the source domain. Accordingly, we propose to filter out source samples of outlier classes by weight suppression and align the distributions of shared classes between the source and target domains by adversarial learning. To learn accurate weight assignment for filtering out outlier classes, we design cycle transformations based on domain prototypes and soft nearest neighbor, where center losses are introduced in individual domains to reduce the intra-class variation. Experiment results on three benchmark datasets demonstrate the effectiveness of our proposed method.

K. Lin and J. Zhou—Equal contributions.

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
EUR 32.99 /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
EUR 29.95
Price includes VAT (Germany)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
EUR 93.08
Price includes VAT (Germany)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
EUR 117.69
Price includes VAT (Germany)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free ship** worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 95–104 (2017)

    Google Scholar 

  2. Bucci, S., D’Innocente, A., Tommasi, T.: Tackling partial domain adaptation with self-supervision. In: International Conference on Image Analysis and Processing, vol. 11752, pp. 70–81 (2019)

    Google Scholar 

  3. Busto, P.P., Gall, J.: Open set domain adaptation. In: IEEE International Conference on Computer Vision, pp. 754–763 (2017)

    Google Scholar 

  4. Cao, Z., Long, M., Wang, J., Jordan, M.I.: Partial transfer learning with selective adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2724–2732 (2018)

    Google Scholar 

  5. Cao, Z., Ma, L., Long, M., Wang, J.: Partial adversarial domain adaptation. In: Proceedings of the European Conference on Computer Vision, pp. 139–155 (2018)

    Google Scholar 

  6. Cao, Z., You, K., Long, M., Wang, J., Yang, Q.: Learning to transfer examples for partial domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2985–2994 (2019)

    Google Scholar 

  7. Chen, C., Li, J., Zheng, Z., Huang, Y., Ding, X., Yu, Y.: Dual bipartite graph learning: a general approach for domain adaptive object detection. In: IEEE/CVF International Conference on Computer Vision, pp. 2683–2692 (2021)

    Google Scholar 

  8. Chen, Z., Chen, C., Cheng, Z., Jiang, B., Fang, K., **, X.: Selective transfer with reinforced transfer network for partial domain adaptation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12703–12711 (2020)

    Google Scholar 

  9. Cui, S., Wang, S., Zhuo, J., Su, C., Huang, Q., Tian, Q.: Gradually vanishing bridge for adversarial domain adaptation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12452–12461 (2020)

    Google Scholar 

  10. Damodaran, B.B., Kellenberger, B., Flamary, R., Tuia, D., Courty, N.: DeepJDOT: deep joint distribution optimal transport for unsupervised domain adaptation. In: Proceedings of the European Conference on Computer Vision, pp. 467–483 (2018)

    Google Scholar 

  11. Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009)

    Google Scholar 

  12. Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: Temporal cycle-consistency learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1801–1810 (2019)

    Google Scholar 

  13. French, G., Mackiewicz, M., Fisher, M.H.: Self-ensembling for visual domain adaptation. In: International Conference on Learning Representations (2018)

    Google Scholar 

  14. Fu, B., Cao, Z., Long, M., Wang, J.: Learning to detect open classes for universal domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 567–583. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_34

    Chapter  Google Scholar 

  15. Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17, 59:1–59:35 (2016)

    Google Scholar 

  16. Goldberger, J., Roweis, S.T., Hinton, G.E., Salakhutdinov, R.: Neighbourhood components analysis. In: Advances in Neural Information Processing Systems, pp. 513–520 (2004)

    Google Scholar 

  17. Goodfellow, I.J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)

    Google Scholar 

  18. Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: Advances in Neural Information Processing Systems, pp. 529–536 (2004)

    Google Scholar 

  19. Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset (2007)

    Google Scholar 

  20. Gu, X., Yu, X., Yang, Y., Sun, J., Xu, Z.: Adversarial reweighting for partial domain adaptation. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  21. Häusser, P., Frerix, T., Mordvintsev, A., Cremers, D.: Associative domain adaptation. In: IEEE International Conference on Computer Vision, pp. 2784–2792 (2017)

    Google Scholar 

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

    Google Scholar 

  23. Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning, vol. 80, pp. 1994–2003 (2018)

    Google Scholar 

  24. Hsu, T.H., Chen, W., Hou, C., Tsai, Y.H., Yeh, Y., Wang, Y.F.: Unsupervised domain adaptation with imbalanced cross-domain data. In: IEEE International Conference on Computer Vision, pp. 4121–4129 (2015)

    Google Scholar 

  25. Hu, J., Tuo, H., Wang, C., Qiao, L., Zhong, H., **g, Z.: Multi-weight partial domain adaptation. In: 30th British Machine Vision Conference, p. 5 (2019)

    Google Scholar 

  26. Hu, J., et al.: Discriminative partial domain adversarial network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 632–648. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58583-9_38

    Chapter  Google Scholar 

  27. Hu, L., Kan, M., Shan, S., Chen, X.: Duplex generative adversarial network for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1498–1507 (2018)

    Google Scholar 

  28. **, 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 

  29. **g, T., **a, H., Ding, Z.: Adaptively-accumulated knowledge transfer for partial domain adaptation. In: ACM International Conference on Multimedia, pp. 1606–1614 (2020)

    Google Scholar 

  30. Kang, G., Wei, Y., Yang, Y., Zhuang, Y., Hauptmann, A.G.: Pixel-level cycle association: a new perspective for domain adaptive semantic segmentation. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems (2020)

    Google Scholar 

  31. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1106–1114 (2012)

    Google Scholar 

  32. Kundu, J.N., Venkat, N., Revanur, A., V., R.M., Babu, R.V.: Towards inheritable models for open-set domain adaptation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12373–12382 (2020)

    Google Scholar 

  33. Kundu, J.N., Venkat, N., V., R.M., Babu, R.V.: Universal source-free domain adaptation. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4543–4552 (2020)

    Google Scholar 

  34. Li, G., Kang, G., Zhu, Y., Wei, Y., Yang, Y.: Domain consensus clustering for universal domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9757–9766 (2021)

    Google Scholar 

  35. Li, S., Liu, C.H., Lin, Q., Wen, Q., Su, L., Huang, G., Ding, Z.: Deep residual correction network for partial domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 43(7), 2329–2344 (2021)

    Article  Google Scholar 

  36. Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. In: Proceedings of the 37th International Conference on Machine Learning, vol. 119, pp. 6028–6039 (2020)

    Google Scholar 

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

    Google Scholar 

  38. Liang, J., Hu, D., Wang, Y., He, R., Feng, J.: Source data-absent unsupervised domain adaptation through hypothesis transfer and labeling transfer. IEEE Trans. Pattern Anal. Mach. Intell. (2021)

    Google Scholar 

  39. Liang, J., Wang, Y., Hu, D., He, R., Feng, J.: A balanced and uncertainty-aware approach for partial domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 123–140. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_8

    Chapter  Google Scholar 

  40. Liu, H., Cao, Z., Long, M., Wang, J., Yang, Q.: Separate to adapt: open set domain adaptation via progressive separation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2927–2936 (2019)

    Google Scholar 

  41. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)

    Google Scholar 

  42. Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: Proceedings of the 32nd International Conference on Machine Learning, vol. 37, pp. 97–105 (2015)

    Google Scholar 

  43. Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems, pp. 1647–1657 (2018)

    Google Scholar 

  44. Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems, pp. 136–144 (2016)

    Google Scholar 

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

    Google Scholar 

  46. Matsuura, T., Saito, K., Harada, T.: TWINs: two weighted inconsistency-reduced networks for partial domain adaptation. CoRR abs/1812.07405 (2018)

    Google Scholar 

  47. Murez, Z., Kolouri, S., Kriegman, D.J., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4500–4509 (2018)

    Google Scholar 

  48. Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)

    Article  Google Scholar 

  49. Peng, X., Usman, B., Kaushik, N., Hoffman, J., Wang, D., Saenko, K.: VisDA: the visual domain adaptation challenge. CoRR abs/1710.06924 (2017)

    Google Scholar 

  50. Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91–99 (2015)

    Google Scholar 

  51. 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 

  52. Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 2988–2997 (2017)

    Google Scholar 

  53. Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3723–3732 (2018)

    Google Scholar 

  54. Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 156–171. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01228-1_10

    Chapter  Google Scholar 

  55. Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to Adapt: aligning domains using generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8503–8512 (2018)

    Google Scholar 

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

    Google Scholar 

  57. Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)

    Google Scholar 

  58. Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_35

    Chapter  Google Scholar 

  59. Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2962–2971 (2017)

    Google Scholar 

  60. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. CoRR abs/1412.3474 (2014)

    Google Scholar 

  61. Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5385–5394 (2017)

    Google Scholar 

  62. Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46478-7_31

    Chapter  Google Scholar 

  63. **ao, W., Ding, Z., Liu, H.: Implicit semantic response alignment for partial domain adaptation. In: Advances in Neural Information Processing Systems (2021)

    Google Scholar 

  64. **e, S., Zheng, Z., Chen, L., Chen, C.: Learning semantic representations for unsupervised domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning, pp. 5419–5428 (2018)

    Google Scholar 

  65. Xu, R., Li, G., Yang, J., Lin, L.: Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation. In: IEEE/CVF International Conference on Computer Vision, pp. 1426–1435 (2019)

    Google Scholar 

  66. Yang, J., Zou, H., Zhou, Y., Zeng, Z., **e, L.: Mind the Discriminability: Asymmetric adversarial domain adaptation. In: Proceedings of the European Conference on Computer Vision. pp. 589–606 (2020)

    Google Scholar 

  67. Yang, S., Wang, Y., van de Weijer, J., Herranz, L., Jui, S.: Exploiting the intrinsic neighborhood structure for source-free domain adaptation. CoRR abs/2110.04202 (2021)

    Google Scholar 

  68. Yang, S., Wang, Y., van de Weijer, J., Herranz, L., Jui, S.: Generalized source-free domain adaptation. In: IEEE/CVF International Conference on Computer Vision, pp. 8978–8987 (2021)

    Google Scholar 

  69. Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: Advances in Neural Information Processing Systems, pp. 3320–3328 (2014)

    Google Scholar 

  70. You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2720–2729 (2019)

    Google Scholar 

  71. Zellinger, W., Grubinger, T., Lughofer, E., Natschläger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning. In: International Conference on Learning Representations (2017)

    Google Scholar 

  72. Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8156–8164 (2018)

    Google Scholar 

  73. Zhang, Y., Zhang, H., Deng, B., Li, S., Jia, K., Zhang, L.: Semi-supervised models are strong unsupervised domain adaptation learners. CoRR abs/2106.00417 (2021)

    Google Scholar 

  74. Zhang, Y., Liu, T., Long, M., Jordan, M.I.: Bridging theory and algorithm for domain adaptation. In: Proceedings of the 36th International Conference on Machine Learning, vol. 97, pp. 7404–7413 (2019)

    Google Scholar 

  75. Zhu, J., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision, pp. 2242–2251 (2017)

    Google Scholar 

Download references

Acknowledgements

This work was supported partially by the NSFC (U21A2-0471, U1911401, U1811461), Guangdong NSF Project (No. 2020B1515120085, 2018B030312002), Guangzhou Research Project (201902010037), and the Key-Area Research and Development Program of Guangzhou (202007030004).

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China

    Kun-Yu Lin, Jiaming Zhou, Yukun Qiu & Wei-Shi Zheng

  2. Peng Cheng Laboratory, Shenzhen, China

    Wei-Shi Zheng

  3. Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, Guangzhou, China

    Wei-Shi Zheng

  4. Guangdong Province Key Laboratory of Information Security Technology, Sun Yat-sen University, Guangzhou, China

    Wei-Shi Zheng

Authors
  1. Kun-Yu Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiaming Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yukun Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wei-Shi Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wei-Shi Zheng .

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 928 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

Lin, KY., Zhou, J., Qiu, Y., Zheng, WS. (2022). Adversarial Partial Domain Adaptation by Cycle Inconsistency. 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_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19827-4_31

  • 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

Search

Navigation