Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

CNG-SFDA: Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15479))

Included in the following conference series:

  • 68 Accesses

Abstract

Domain shift occurs when training (source) and test (target) data diverge in their distribution. Source-Free Domain Adaptation (SFDA) addresses this domain shift problem, aiming to adopt a trained model on the source domain to the target domain in a scenario where only a well-trained source model and unlabeled target data are available. In this scenario, handling false labels in the target domain is crucial because they negatively impact the model performance. To deal with this problem, we propose to update cluster prototypes (i.e., centroid of each sample cluster) and their structure in the target domain formulated by the source model in online manners. In the feature space, samples in different regions have different pseudo-label distribution characteristics affected by the cluster prototypes, and we adopt distinct training strategies for these samples by defining clean and noisy regions: we selectively train the target with clean pseudo-labels in the clean region, whereas we introduce mix-up inputs representing intermediate features between clean and noisy regions to increase the compactness of the cluster. We conducted extensive experiments on multiple datasets in online/offline SFDA settings, whose results demonstrate that our method, CNG-SFDA, achieves state-of-the-art for most cases. Code is available at https://github.com/hyeonwoocho7/CNG-SFDA.

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
eBook
USD 139.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
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

Similar content being viewed by others

References

  1. Ahmed, S.M., Raychaudhuri, D.S., Paul, S., Oymak, S., Roy-Chowdhury, A.K.: Unsupervised multi-source domain adaptation without access to source data. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 10103–10112 (2021)

    Google Scholar 

  2. Ahmed, W., Morerio, P., Murino, V.: Cleaning noisy labels by negative ensemble learning for source-free unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. pp. 1616–1625 (2022)

    Google Scholar 

  3. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3722–3731 (2017)

    Google Scholar 

  4. Chen, D., Wang, D., Darrell, T., Ebrahimi, S.: Contrastive test-time adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 295–305 (2022)

    Google Scholar 

  5. Chen, L., Chen, H., Wei, Z., Jin, X., Tan, X., Jin, Y., Chen, E.: 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 

  6. Cho, H., Nishimura, K., Watanabe, K., Bise, R.: Effective pseudo-labeling based on heatmap for unsupervised domain adaptation in cell detection. Med. Image Anal. 79, 102436 (2022)

    Article  Google Scholar 

  7. Choi, J., Jeong, M., Kim, T., Kim, C.: Pseudo-labeling curriculum for unsupervised domain adaptation. arXiv preprint arXiv:1908.00262 (2019)

  8. Choi, S., Yang, S., Choi, S., Yun, S.: Improving test-time adaptation via shift-agnostic weight regularization and nearest source prototypes. In: European Conference on Computer Vision. pp. 440–458. Springer (2022)

    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 IEEE/CVF conference on computer vision and pattern recognition. pp. 12455–12464 (2020)

    Google Scholar 

  10. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248–255. Ieee (2009)

    Google Scholar 

  11. Ding, N., Xu, Y., Tang, Y., Xu, C., Wang, Y., Tao, D.: Source-free domain adaptation via distribution estimation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7212–7222 (2022)

    Google Scholar 

  12. Ding, Y., Sheng, L., Liang, J., Zheng, A., He, R.: Proxymix: Proxy-based mixup training with label refinery for source-free domain adaptation. Neural Netw. 167, 92–103 (2023)

    Article  Google Scholar 

  13. Döbler, M., Marsden, R.A., Yang, B.: Robust mean teacher for continual and gradual test-time adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7704–7714 (2023)

    Google Scholar 

  14. Du, Y., Yang, H., Chen, M., Luo, H., Jiang, J., Xin, Y., Wang, C.: Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation. Machine Learning pp. 1–21 (2023)

    Google Scholar 

  15. Frikha, A., Chen, H., Krompaß, D., Runkler, T., Tresp, V.: Towards data-free domain generalization. In: Asian Conference on Machine Learning. pp. 327–342. PMLR (2023)

    Google Scholar 

  16. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International conference on machine learning. pp. 1180–1189. PMLR (2015)

    Google Scholar 

  17. Gulrajani, I., Lopez-Paz, D.: In search of lost domain generalization. arXiv preprint arXiv:2007.01434 (2020)

  18. 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 

  19. He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14. pp. 630–645. Springer (2016)

    Google Scholar 

  20. Hu, S.X., Moreno, P.G., Xiao, Y., Shen, X., Obozinski, G., Lawrence, N.D., Damianou, A.: Empirical bayes transductive meta-learning with synthetic gradients. arXiv preprint arXiv:2004.12696 (2020)

  21. Huynh, T., Kornblith, S., Walter, M.R., Maire, M., Khademi, M.: Boosting contrastive self-supervised learning with false negative cancellation. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision. pp. 2785–2795 (2022)

    Google Scholar 

  22. Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. pp. 448–456. pmlr (2015)

    Google Scholar 

  23. Jin, Y., Wang, X., Long, M., Wang, J.: Minimum class confusion for versatile domain adaptation. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXI 16. pp. 464–480. Springer (2020)

    Google Scholar 

  24. 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 

  25. Karim, N., Mithun, N.C., Rajvanshi, A., Chiu, H.p., Samarasekera, S., Rahnavard, N.: C-sfda: A curriculum learning aided self-training framework for efficient source free domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 24120–24131 (2023)

    Google Scholar 

  26. Kim, S., Lee, G., Bae, S., Yun, S.Y.: Mixco: Mix-up contrastive learning for visual representation. arXiv preprint arXiv:2010.06300 (2020)

  27. Kong, L., Xie, S., Yao, W., Zheng, Y., Chen, G., Stojanov, P., Akinwande, V., Zhang, K.: Partial disentanglement for domain adaptation. In: International Conference on Machine Learning. pp. 11455–11472. PMLR (2022)

    Google Scholar 

  28. Lee, J., Jung, D., Yim, J., Yoon, S.: Confidence score for source-free unsupervised domain adaptation. In: International Conference on Machine Learning. pp. 12365–12377. PMLR (2022)

    Google Scholar 

  29. Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: Proceedings of the IEEE international conference on computer vision. pp. 5542–5550 (2017)

    Google Scholar 

  30. Li, R., Jia, X., He, J., Chen, S., Hu, Q.: T-svdnet: Exploring high-order prototypical correlations for multi-source domain adaptation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 9991–10000 (2021)

    Google Scholar 

  31. 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. PMLR (2020)

    Google Scholar 

  32. 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. 44(11), 8602–8617 (2021)

    Google Scholar 

  33. Litrico, M., Del Bue, A., Morerio, P.: Guiding pseudo-labels with uncertainty estimation for source-free unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7640–7650 (2023)

    Google Scholar 

  34. Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. Advances in neural information processing systems 31 (2018)

    Google Scholar 

  35. Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. Advances in neural information processing systems 29 (2016)

    Google Scholar 

  36. Mahajan, D., Tople, S., Sharma, A.: Domain generalization using causal matching. In: International Conference on Machine Learning. pp. 7313–7324. PMLR (2021)

    Google Scholar 

  37. Mitchell, H.B., Schaefer, P.A.: A “soft” k-nearest neighbor voting scheme. Int. J. Intell. Syst. 16(4), 459–468 (2001)

    Google Scholar 

  38. Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4500–4509 (2018)

    Google Scholar 

  39. 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 

  40. Nam, H., Lee, H., Park, J., Yoon, W., Yoo, D.: Reducing domain gap by reducing style bias. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 8690–8699 (2021)

    Google Scholar 

  41. Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)

  42. 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 

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

  44. Reynolds, D.A., et al.: Gaussian mixture models. Encyclopedia of biometrics 741(659-663) (2009)

    Google Scholar 

  45. 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 

  46. 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 

  47. Salimans, T., Kingma, D.P.: Weight normalization: A simple reparameterization to accelerate training of deep neural networks. Advances in neural information processing systems 29 (2016)

    Google Scholar 

  48. Tomar, D., Vray, G., Bozorgtabar, B., Thiran, J.P.: Tesla: Test-time self-learning with automatic adversarial augmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 20341–20350 (2023)

    Google Scholar 

  49. 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 

  50. Vapnik, V.N.: Statistical Learning Theory. Wiley-Interscience (1998)

    Google Scholar 

  51. Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: Fully test-time adaptation by entropy minimization. arXiv preprint arXiv:2006.10726 (2020)

  52. Wang, Q., Fink, O., Van Gool, L., Dai, D.: Continual test-time domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7201–7211 (2022)

    Google Scholar 

  53. Wang, S., Zhang, D., Yan, Z., Zhang, J., Li, R.: Feature alignment and uniformity for test time adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 20050–20060 (2023)

    Google Scholar 

  54. Wilson, G., Cook, D.J.: A survey of unsupervised deep domain adaptation. ACM Transactions on Intelligent Systems and Technology (TIST) 11(5), 1–46 (2020)

    Article  Google Scholar 

  55. Xu, Q., Zhang, R., Zhang, Y., Wang, Y., Tian, Q.: A fourier-based framework for domain generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14383–14392 (2021)

    Google Scholar 

  56. Xu, R., Liu, P., Wang, L., Chen, C., Wang, J.: Reliable weighted optimal transport for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4394–4403 (2020)

    Google Scholar 

  57. Yang, S., Jui, S., van de Weijer, J., et al.: Attracting and dispersing: A simple approach for source-free domain adaptation. Adv. Neural. Inf. Process. Syst. 35, 5802–5815 (2022)

    Google Scholar 

  58. Yang, S., van de Weijer, J., Herranz, L., Jui, S., et al.: Exploiting the intrinsic neighborhood structure for source-free domain adaptation. Adv. Neural. Inf. Process. Syst. 34, 29393–29405 (2021)

    Google Scholar 

  59. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)

  60. Zhang, P., Zhang, B., Zhang, T., Chen, D., Wang, Y., Wen, F.: Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 12414–12424 (2021)

    Google Scholar 

  61. Zhang, W., Ouyang, W., Li, W., Xu, D.: Collaborative and adversarial network for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3801–3809 (2018)

    Google Scholar 

  62. Zhang, W., Zhu, L., Hallinan, J., Zhang, S., Makmur, A., Cai, Q., Ooi, B.C.: Boostmis: Boosting medical image semi-supervised learning with adaptive pseudo labeling and informative active annotation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 20666–20676 (2022)

    Google Scholar 

  63. Zhang, Y., Wang, X., Jin, K., Yuan, K., Zhang, Z., Wang, L., Jin, R., Tan, T.: Adanpc: Exploring non-parametric classifier for test-time adaptation. In: International Conference on Machine Learning. pp. 41647–41676. PMLR (2023)

    Google Scholar 

  64. Zhang, Y., Wang, Z., He, W.: Class relationship embedded learning for source-free unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 7619–7629 (2023)

    Google Scholar 

  65. Zhang, Z., Chen, W., Cheng, H., Li, Z., Li, S., Lin, L., Li, G.: Divide and contrast: Source-free domain adaptation via adaptive contrastive learning. Adv. Neural. Inf. Process. Syst. 35, 5137–5149 (2022)

    Google Scholar 

Download references

Acknowledgements

This research was conducted with resources and endless support from VUNO Inc, and Won Hwa Kim was supported by Graduate School of AI at POSTECH (IITP-2019-0-01906).

Author information

Authors and Affiliations

  1. VUNO Inc., Seoul, South Korea

    Hyeonwoo Cho, Dong-Hee Kim & Jinyoung Kim

  2. POSCO DX, Pohang-si, South Korea

    Chanmin Park

  3. POSTECH, Pohang-si, South Korea

    Won Hwa Kim

Authors
  1. Hyeonwoo Cho
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chanmin Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dong-Hee Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jinyoung Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Won Hwa Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hyeonwoo Cho .

Editor information

Editors and Affiliations

  1. Pohang University of Science and Technology (POSTECH), Pohang, Korea (Republic of)

    Minsu Cho

  2. Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

    Ivan Laptev

  3. Google, Mountain View, CA, USA

    Du Tran

  4. National University of Singapore, Singapore, Singapore

    Angela Yao

  5. Peking University, Beijing, China

    Hongbin Zha

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2327 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Cho, H., Park, C., Kim, DH., Kim, J., Kim, W.H. (2025). CNG-SFDA: Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation. In: Cho, M., Laptev, I., Tran, D., Yao, A., Zha, H. (eds) Computer Vision – ACCV 2024. ACCV 2024. Lecture Notes in Computer Science, vol 15479. Springer, Singapore. https://doi.org/10.1007/978-981-96-0966-6_9

Download citation

  • DOI: https://doi.org/10.1007/978-981-96-0966-6_9

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-96-0965-9

  • Online ISBN: 978-981-96-0966-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation