Skip to main content

Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-training Strategies and Performance Insights

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15112))

Included in the following conference series:

  • 259 Accesses

Abstract

This paper focuses on source-free domain adaptation for object detection in computer vision. This task is challenging and of great practical interest, due to the cost of obtaining annotated data sets for every new domain. Recent research has proposed various solutions for Source-Free Object Detection (SFOD), most being variations of teacher-student architectures with diverse feature alignment, regularization and pseudo-label selection strategies. Our work investigates simpler approaches and their performance compared to more complex SFOD methods in several adaptation scenarios. We highlight the importance of batch normalization layers in the detector backbone, and show that adapting only the batch statistics is a strong baseline for SFOD. We propose a simple extension of a Mean Teacher with strong-weak augmentation in the source-free setting, Source-Free Unbiased Teacher (SF-UT), and show that it actually outperforms most of the previous SFOD methods. Additionally, we showcase that an even simpler strategy consisting in training on a fixed set of pseudo-labels can achieve similar performance to the more complex teacher-student mutual learning, while being computationally efficient and mitigating the major issue of teacher-student collapse. We conduct experiments on several adaptation tasks using benchmark driving datasets including (Foggy)Cityscapes, Sim10k and KITTI, and achieve a notable improvement of 4.7% AP50 on Cityscapes\(\rightarrow \)Foggy-Cityscapes compared with the latest state-of-the-art in SFOD. Source code is available at https://github.com/EPFL-IMOS/simple-SFOD.

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

Access this chapter

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

References

  1. Cai, Q., Pan, Y., Ngo, C.W., Tian, X., Duan, L., Yao, T.: Exploring object relation in mean teacher for cross-domain detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11457–11466 (2019)

    Google Scholar 

  2. Chang, W.G., You, T., Seo, S., Kwak, S., Han, B.: Domain-specific batch normalization for unsupervised domain adaptation. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7346–7354 (2019). https://doi.org/10.1109/CVPR.2019.00753. https://ieeexplore.ieee.org/document/8953938. ISSN 2575-7075

  3. Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster R-CNN for object detection in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3339–3348 (2018)

    Google Scholar 

  4. Chen, Z., Wang, Z., Zhang, Y.: Exploiting low-confidence pseudo-labels for source-free object detection (2023). https://doi.org/10.1145/3581783.3612273, [cs]

  5. Chu, Q., Li, S., Chen, G., Li, K., Li, X.: Adversarial alignment for source free object detection (2023). https://doi.org/10.48550/arXiv.2301.04265, [cs]

  6. Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)

    Google Scholar 

  7. Courty, N., Flamary, R., Habrard, A., Rakotomamonjy, A.: Joint distribution optimal transportation for domain adaptation. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper/2017/hash/0070d23b06b1486a538c0eaa45dd167a-Abstract.html

  8. Deng, J., Li, W., Chen, Y., Duan, L.: Unbiased mean teacher for cross-domain object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4091–4101 (2021)

    Google Scholar 

  9. Duan, L., Tsang, I.W., Xu, D.: Domain transfer multiple kernel learning. IEEE Trans. Pattern Anal. Mach. Intell. 34(3), 465–479 (2012)

    Article  Google Scholar 

  10. Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(59), 1–35 (2016). http://jmlr.org/papers/v17/15-239.html

  11. Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: YOLOX: exceeding YOLO series in 2021. arXiv preprint arXiv:2107.08430 (2021)

  12. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)

    Google Scholar 

  13. Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440–1448 (2015)

    Google Scholar 

  14. Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2066–2073. IEEE (2012)

    Google Scholar 

  15. He, Z., Zhang, L.: Domain adaptive object detection via asymmetric tri-way faster-RCNN. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 309–324. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58586-0_19

    Chapter  Google Scholar 

  16. Huang, J., Guan, D., Xiao, A., Lu, S.: Model adaptation: historical contrastive learning for unsupervised domain adaptation without source data. In: Advances in Neural Information Processing Systems, vol. 34, pp. 3635–3649 (2021)

    Google Scholar 

  17. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). https://doi.org/10.48550/arXiv.1502.03167, [cs]

  18. Johnson-Roberson, M., Barto, C., Mehta, R., Sridhar, S.N., Rosaen, K., Vasudevan, R.: Driving in the matrix: can virtual worlds replace human-generated annotations for real world tasks? In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 746–753. IEEE (2017)

    Google Scholar 

  19. Khodabandeh, M., Vahdat, A., Ranjbar, M., Macready, W.G.: A robust learning approach to domain adaptive object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 480–490 (2019)

    Google Scholar 

  20. Klingner, M., Termöhlen, J.A., Ritterbach, J., Fingscheidt, T.: Unsupervised BatchNorm Adaptation (UBNA): a domain adaptation method for semantic segmentation without using source domain representations (2021). https://doi.org/10.48550/arXiv.2011.08502, [cs]

  21. Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning (2017). https://doi.org/10.48550/arXiv.1610.02242, [cs]

  22. Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML 2013 Workshop: Challenges in Representation Learning (WREPL) (2013)

    Google Scholar 

  23. Li, C., et al.: Spatial attention pyramid network for unsupervised domain adaptation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 481–497. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58601-0_29

    Chapter  Google Scholar 

  24. Li, S., Ye, M., Zhu, X., Zhou, L., Xiong, L.: Source-free object detection by learning to overlook domain style. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8014–8023 (2022)

    Google Scholar 

  25. Li, X., et al.: A free lunch for unsupervised domain adaptive object detection without source data. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 8474–8481 (2021)

    Google Scholar 

  26. Li, Y., Wang, N., Shi, J., Hou, X., Liu, J.: Adaptive batch normalization for practical domain adaptation. Pattern Recogn. 80, 109–117 (2018)

    Article  Google Scholar 

  27. Li, Y.J., et al.: Cross-domain adaptive teacher for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7581–7590 (2022)

    Google Scholar 

  28. Liu, Q., Lin, L., Shen, Z., Yang, Z.: Periodically exchange teacher-student for source-free object detection. In: ICCV 2023 (2023)

    Google Scholar 

  29. Liu, Y.C., et al.: Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480 (2021)

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

    Google Scholar 

  31. Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018). https://proceedings.neurips.cc/paper/2018/hash/ab88b15733f543179858600245108dd8-Abstract.html

  32. Pan, X., Luo, P., Shi, J., Tang, X.: Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net (2018). https://openaccess.thecvf.com/content_ECCV_2018/html/Xingang_Pan_Two_at_Once_ECCV_2018_paper.html

  33. Rangwani, H., Aithal, S.K., Mishra, M., Jain, A., Babu, R.V.: A closer look at smoothness in domain adversarial training (2022). https://doi.org/10.48550/arXiv.2206.08213, [cs]

  34. Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)

    Google Scholar 

  35. Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 6949–6958. IEEE (2019). https://doi.org/10.1109/CVPR.2019.00712. https://ieeexplore.ieee.org/document/8954336/

  36. 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 

  37. Seo, S., Suh, Y., Kim, D., Kim, G., Han, J., Han, B.: Learning to optimize domain specific normalization for domain generalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 68–83. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58542-6_5

    Chapter  Google Scholar 

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

  39. Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: Advances in Neural Information Processing Systems, vol. 33, pp. 596–608 (2020)

    Google Scholar 

  40. Su, P., et al.: Adapting object detectors with conditional domain normalization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 403–419. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58621-8_24

    Chapter  Google Scholar 

  41. 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 

  42. Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization (2017). https://doi.org/10.48550/arXiv.1607.08022, [cs]

  43. Vs, V., Gupta, V., Oza, P., Sindagi, V.A., Patel, V.M.: Mega-CDA: memory guided attention for category-aware unsupervised domain adaptive object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4516–4526 (2021)

    Google Scholar 

  44. VS, V., Oza, P., Patel, V.M.: Instance relation graph guided source-free domain adaptive object detection (2023). https://doi.org/10.48550/arXiv.2203.15793, [cs]

  45. Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization (2021). https://doi.org/10.48550/arXiv.2006.10726, [cs, stat]

  46. Wei, X., et al.: Entropy-minimization mean teacher for source-free domain adaptive object detection. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds.) ICONIP 2022. LNCS, vol. 13623, pp. 513–524. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-30105-6_43

    Chapter  Google Scholar 

  47. Xiong, L., Ye, M., Zhang, D., Gan, Y., Li, X., Zhu, Y.: Source data-free domain adaptation of object detector through domain-specific perturbation. Int. J. Intell. Syst. 36(8), 3746–3766 (2021)

    Article  Google Scholar 

  48. Xu, C.D., Zhao, X.R., Jin, X., Wei, X.S.: Exploring categorical regularization for domain adaptive object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11724–11733 (2020)

    Google Scholar 

  49. Zhang, C., et al.: Self-guided adaptation: progressive representation alignment for domain adaptive object detection. IEEE Trans. Multimed. 24, 2246–2258 (2021)

    Article  Google Scholar 

  50. Zhang, J., Qi, L., Shi, Y., Gao, Y.: Generalizable model-agnostic semantic segmentation via target-specific normalization. Pattern Recogn. 122 (2022). https://doi.org/10.1016/j.patcog.2021.108292. https://www.sciencedirect.com/science/article/pii/S0031320321004726

  51. Zhang, S., Zhang, L., Liu, Z.: Refined pseudo labeling for source-free domain adaptive object detection. arXiv preprint arXiv:2303.03728 (2023)

  52. Zhao, G., Li, G., Xu, R., Lin, L.: Collaborative training between region proposal localization and classification for domain adaptive object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 86–102. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58523-5_6

    Chapter  Google Scholar 

  53. Zhao, L., Wang, L.: Task-specific inconsistency alignment for domain adaptive object detection (2022). https://doi.org/10.48550/arXiv.2203.15345, [cs]

  54. Zhao, Z., Guo, Y., Ye, J.: Bi-dimensional feature alignment for cross-domain object detection. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12535, pp. 671–686. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66415-2_46

    Chapter  Google Scholar 

Download references

Acknowledgements

This work has been supported by the SNSF Grant 200021_200461.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Florent Forest .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2381 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 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

Hao, Y., Forest, F., Fink, O. (2025). Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-training Strategies and Performance Insights. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15112. Springer, Cham. https://doi.org/10.1007/978-3-031-72949-2_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72949-2_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72948-5

  • Online ISBN: 978-3-031-72949-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics