Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

A Balanced and Uncertainty-Aware Approach for Partial Domain Adaptation

  • Conference paper
  • First Online:

Abstract

This work addresses the unsupervised domain adaptation problem, especially in the case of class labels in the target domain being only a subset of those in the source domain. Such a partial transfer setting is realistic but challenging and existing methods always suffer from two key problems, negative transfer and uncertainty propagation. In this paper, we build on domain adversarial learning and propose a novel domain adaptation method BA\(^3\)US with two new techniques termed Balanced Adversarial Alignment (BAA) and Adaptive Uncertainty Suppression (AUS), respectively. On one hand, negative transfer results in misclassification of target samples to the classes only present in the source domain. To address this issue, BAA pursues the balance between label distributions across domains in a fairly simple manner. Specifically, it randomly leverages a few source samples to augment the smaller target domain during domain alignment so that classes in different domains are symmetric. On the other hand, a source sample would be denoted as uncertain if there is an incorrect class that has a relatively high prediction score, and such uncertainty easily propagates to unlabeled target data around it during alignment, which severely deteriorates adaptation performance. Thus we present AUS that emphasizes uncertain samples and exploits an adaptive weighted complement entropy objective to encourage incorrect classes to have uniform and low prediction scores. Experimental results on multiple benchmarks demonstrate our BA\(^3\)US surpasses state-of-the-arts for partial domain adaptation tasks. Code is available athttps://github.com/tim-learn/BA3US.

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

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /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
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11439
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14299
Price includes VAT (Japan)
  • 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

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. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: Proceedings of the CVPR, pp. 3722–3731 (2017)

    Google Scholar 

  3. Bucci, S., D’Innocente, A., Tommasi, T.: Tackling partial domain adaptation with self-supervision. arXiv preprintarXiv:1906.05199 (2019)

  4. Cao, Z., Long, M., Wang, J., Jordan, M.I.: Partial transfer learning with selective adversarial networks. In: Proceedings of the CVPR, pp. 2724–2732 (2018)

    Google Scholar 

  5. Cao, Z., Ma, L., Long, M., Wang, J.: Partial adversarial domain adaptation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 139–155. Springer, Cham (2018).https://doi.org/10.1007/978-3-030-01237-3_9

    Chapter  Google Scholar 

  6. Cao, Z., You, K., Long, M., Wang, J., Yang, Q.: Learning to transfer examples for partial domain adaptation. In: Proceedings of the CVPR, pp. 2985–2994 (2019)

    Google Scholar 

  7. Chen, H.Y., et al.: Complement objective training. In: Proceedings of the ICLR (2019)

    Google Scholar 

  8. Csurka, G.: Domain adaptation for visual applications: A comprehensive survey. arXiv preprintarXiv:1702.05374 (2017)

  9. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: Proceedings of the ICML, pp. 1180–1189 (2015)

    Google Scholar 

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

    MathSciNet MATH  Google Scholar 

  11. Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 597–613. Springer, Cham (2016).https://doi.org/10.1007/978-3-319-46493-0_36

    Chapter  Google Scholar 

  12. Goodfellow, I., et al.: Generative adversarial nets. In: Proceedings of the NeurIPS, pp. 2672–2680 (2014)

    Google Scholar 

  13. Grandvalet, Y., Bengio, Y.: Semi-supervised learning by entropy minimization. In: Proceedings of the NeurIPS, pp. 529–536 (2005)

    Google Scholar 

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

    Google Scholar 

  15. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the CVPR, pp. 770–778 (2016)

    Google Scholar 

  16. Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: Proceedings of the ICML, pp. 1989–1998 (2018)

    Google Scholar 

  17. Hu, J., Wang, C., Qiao, L., Zhong, H., Jing, Z.: Multi-weight partial domain adaptation. In: Proceedings of the BMVC (2019)

    Google Scholar 

  18. Koniusz, P., Tas, Y., Porikli, F.: Domain adaptation by mixture of alignments of second-or higher-order scatter tensors. In: Proceedings of the CVPR, pp. 7139–7148 (2017)

    Google Scholar 

  19. Kouw, W.M., Loog, M.: A review of single-source unsupervised domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. (2019, in press)

    Google Scholar 

  20. Kumar, A., et al.: Co-regularized alignment for unsupervised domain adaptation. In: Proceedings of the NeurIPS, pp. 9345–9356 (2018)

    Google Scholar 

  21. Li, S., et al.: Deep residual correction network for partial domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. (2020, in press)

    Google Scholar 

  22. Liang, J., He, R., Sun, Z., Tan, T.: Aggregating randomized clustering-promoting invariant projections for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell.41(5), 1027–1042 (2019)

    Article  Google Scholar 

  23. Liang, J., He, R., Sun, Z., Tan, T.: Distant supervised centroid shift: a simple and efficient approach to visual domain adaptation. In: Proceedings of the CVPR, pp. 2975–2984 (2019)

    Google Scholar 

  24. Liu, M.Y., Tuzel, O.: Coupled generative adversarial networks. In: Proceedings of the NeurIPS, pp. 469–477 (2016)

    Google Scholar 

  25. Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: Proceedings of the ICML, pp. 97–105 (2015)

    Google Scholar 

  26. Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Proceedings of the NeurIPS, pp. 1647–1657 (2018)

    Google Scholar 

  27. Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: Proceedings of the ICML, pp. 2208–2217 (2017)

    Google Scholar 

  28. van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res.9, 2579–2605 (2008)

    MATH  Google Scholar 

  29. Mao, X., Ma, Y., Yang, Z., Chen, Y., Li, Q.: Virtual mixup training for unsupervised domain adaptation. arXiv preprintarXiv:1905.04215 (2019)

  30. Matsuura, T., Saito, K., Harada, T.: TWINs: Two weighted inconsistency-reduced networks for partial domain adaptation. arXiv preprintarXiv:1812.07405 (2018)

  31. Ming Harry Hsu, T., Yu Chen, W., Hou, C.A., Hubert Tsai, Y.H., Yeh, Y.R., Frank Wang, Y.C.: Unsupervised domain adaptation with imbalanced cross-domain data. In: Proceedings of the ICCV, pp. 4121–4129 (2015)

    Google Scholar 

  32. Miyato, T., Maeda, S., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans. Pattern Anal. Mach. Intell.41(8), 1979–1993 (2018)

    Article  Google Scholar 

  33. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis.115(3), 211–252 (2015)

    Article MathSciNet  Google Scholar 

  34. 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 

  35. Shu, R., Bui, H.H., Narui, H., Ermon, S.: A DIRT-T approach to unsupervised domain adaptation. In: Proceedings of the ICLR (2018)

    Google Scholar 

  36. Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprintarXiv:1409.1556 (2014)

  37. 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 

  38. Tsai, Y.H.H., Hou, C.A., Chen, W.Y., Yeh, Y.R., Wang, Y.C.F.: Domain-constraint transfer coding for imbalanced unsupervised domain adaptation. In: Proceedings of the AAAI, pp. 3597–3603 (2016)

    Google Scholar 

  39. Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the ICCV, pp. 4068–4076 (2015)

    Google Scholar 

  40. Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Proceedings of the CVPR, pp. 2962–2971 (2017)

    Google Scholar 

  41. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: Maximizing for domain invariance. arXiv preprintarXiv:1412.3474 (2014)

  42. Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: Proceedings of the CVPR, pp. 5018–5027 (2017)

    Google Scholar 

  43. Wang, Q., Li, W., Van Gool, L.: Semi-supervised learning by augmented distribution alignment. In: Proceedings of the ICCV, pp. 1466–1475 (2019)

    Google Scholar 

  44. Wang, X., Jin, Y., Long, M., Wang, J., Jordan, M.I.: Transferable normalization: towards improving transferability of deep neural networks. In: Proceedings of the NeurIPS, pp. 1951–1961 (2019)

    Google Scholar 

  45. Wang, Z., Dai, Z., Póczos, B., Carbonell, J.: Characterizing and avoiding negative transfer. In: Proceedings of the CVPR, pp. 11293–11302 (2019)

    Google Scholar 

  46. 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 ICCV, pp. 1426–1435 (2019)

    Google Scholar 

  47. Zellinger, W., Grubinger, T., Lughofer, E., Natschläger, T., Saminger-Platz, S.: Central moment discrepancy (CMD) for domain-invariant representation learning. In: Proceedings of the ICLR (2016)

    Google Scholar 

  48. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: Proceedings of the ICLR (2018)

    Google Scholar 

  49. Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: Proceedings of the CVPR, pp. 8156–8164 (2018)

    Google Scholar 

  50. Zhang, L.: Transfer adaptation learning: A decade survey. arXiv preprintarXiv:1903.04687 (2019)

  51. Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the ICCV, pp. 2223–2232 (2017)

    Google Scholar 

Download references

Acknowledgment

J. Feng was partially supported by NUS ECRA FY17 P08, AISG-100E2019-035, and MOE Tier 2 MOE2017-T2-2-151. The authors also thank Quanhong Fu for her help to improve the technical writing aspect of this paper.

Author information

Authors and Affiliations

  1. Department of ECE, National University of Singapore (NUS), Singapore, Singapore

    Jian Liang, Dapeng Hu & Jiashi Feng

  2. Peking University, Beijing, China

    Yunbo Wang

  3. Institute of Automation, Chinese Academy of Sciences, Beijing, China

    Ran He

Authors
  1. Jian Liang

    You can also search for this author inPubMed Google Scholar

  2. Yunbo Wang

    You can also search for this author inPubMed Google Scholar

  3. Dapeng Hu

    You can also search for this author inPubMed Google Scholar

  4. Ran He

    You can also search for this author inPubMed Google Scholar

  5. Jiashi Feng

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toJian Liang.

Editor information

Editors and Affiliations

  1. University of Oxford, Oxford, UK

    Andrea Vedaldi

  2. Graz University of Technology, Graz, Austria

    Horst Bischof

  3. University of Freiburg, Freiburg im Breisgau, Germany

    Thomas Brox

  4. University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Jan-Michael Frahm

Rights and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Liang, J., Wang, Y., Hu, D., He, R., Feng, J. (2020). A Balanced and Uncertainty-Aware Approach for Partial Domain Adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12356. Springer, Cham. https://doi.org/10.1007/978-3-030-58621-8_8

Download citation

Publish with us

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /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
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 11439
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 14299
Price includes VAT (Japan)
  • 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

[8]ページ先頭
©2009-2025 Movatter.jp