[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Source-free domain adaptive object detection based on pseudo-supervised mean teacher

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Domain adaptive object detection refers to training a cross-domain object detector through a large number of labeled source domain datasets and unlabeled target domain datasets and learning the domain invariant features between two domains to reduce or eliminate the domain discrepancy. However, factors such as data privacy protection, limited storage space, and high labor costs often make many source domain-labeled samples unavailable in real-time situations. In this work, we propose a pseudo-supervised mean teacher model for source-free domain adaptive object detection that alternates between generating pseudo-labels and fine-tuning the model and utilizes a pixel-level distillation loss method and the weight regularization module for model adaptation. We use the mean teacher model to assist training to achieve object detection task in the source-free domain. Experiments are carried out on multiple datasets such as Cityscapes, Foggy Cityscapes, and SIM10K. Extensive experiments on multiple domain adaptation scenarios show that our method achieves better performance than the baseline (Faster R-CNN) and multiple state-of-the-art domain adaptation methods which require access to source domain data, demonstrating the effectiveness and robustness of the proposed method.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Availability of data and materials

Data openly available in a public repository. Cityscapes: https://www.cityscapes-dataset.com/downloads/ Pascal VOC: http://host.robots.ox.ac.uk/pascal/VOC/ SIM10K: https://fcav.engin.umich.edu/projects/driving-in-the-matrix

References

  1. Bochkovskiy A, Wang C-Y, Liao H-YM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934

  2. Chen Y, Li W, Sakaridis C, Dai D, Van Gool L (2018) 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

  3. Hou Y, Zheng L (2021) Visualizing adapted knowledge in domain transfer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13824–13833

  4. Kurmi VK, Subramanian VK, Namboodiri VP (2021) Domain impression: A source data free domain adaptation method. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 615–625

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

  6. Kim Y, Cho D, Han K, Panda P, Hong S (2021) Domain adaptation without source data. IEEE Transact Artifi Intel 2(6):508–518

    Article  Google Scholar 

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

  8. Liang J, Hu D, Feng J (2020) 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

  9. He Z, Zhang L (2020) Domain adaptive object detection via asymmetric tri-way faster-rcnn. In: European Conference on Computer Vision, pp. 309–324. Springer

  10. Han X-F, Laga H, Bennamoun M (2019) Image-based 3d object reconstruction: state-of-the-art and trends in the deep learning era. IEEE Transact Pattern Anal Mach Intell 43(5):1578–1604

    Article  Google Scholar 

  11. Ben-Nun T, Hoefler T (2019) Demystifying parallel and distributed deep learning: an in-depth concurrency analysis. ACM Comput Surv (CSUR) 52(4):1–43

    Article  Google Scholar 

  12. Zheng Y, Huang D, Liu S, Wang Y (2020) Cross-domain object detection through coarse-to-fine feature adaptation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13766–13775

  13. Xie R, Yu F, Wang J, Wang Y, Zhang L (2019) Multi-level domain adaptive learning for cross-domain detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, pp. 0–0

  14. Sadr H, Nazari Soleimandarabi M (2022) Acnn-tl: attention-based convolutional neural network coupling with transfer learning and contextualized word representation for enhancing the performance of sentiment classification. J Supercomput 78(7):10149–10175

    Article  Google Scholar 

  15. Thakkar A, Mungra D, Agrawal A, Chaudhari K (2022) Improving the performance of sentiment analysis using enhanced preprocessing technique and artificial neural network. IEEE transactions on affective computing

  16. Gururangan S, Marasović A, Swayamdipta S, Lo K, Beltagy I, Downey D, Smith NA (2020) Don’t stop pretraining: adapt language models to domains and tasks. arXiv preprint arXiv:2004.10964

  17. Dong J, Cong Y, Sun G, Liu Y, Xu X (2020) Cscl: Critical semantic-consistent learning for unsupervised domain adaptation. In: European Conference on Computer Vision, pp. 745–762. Springer

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

  19. Wang Q, Breckon T (2020) Unsupervised domain adaptation via structured prediction based selective pseudo-labeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 6243–6250

  20. Wang L, Xu S, Wang X, Zhu Q (2019) Eavesdrop the composition proportion of training labels in federated learning. arXiv preprint arXiv:1910.06044

  21. Wang L, Xu S, Wang X, Zhu Q (2020) Towards class imbalance in federated learning

  22. Yang S, Wang Y, van de Weijer J, Herranz L, Jui S (2020) Unsupervised domain adaptation without source data by casting a bait. arXiv preprint arXiv:2010.12427

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

    Article  Google Scholar 

  24. Zhang D, Ye M, Xiong L, Li S, Li X (2021) Source-style transferred mean teacher for source-data free object detection. In: ACM multimedia asia, pp. 1–8

  25. Liu Y-C, Ma C-Y, He Z, Kuo C-W, Chen K, Zhang P, Wu B, Kira Z, Vajda P (2021) Unbiased teacher for semi-supervised object detection. arXiv preprint arXiv:2102.09480

  26. He R, Lee WS, Ng HT, Dahlmeier D (2018) Adaptive semi-supervised learning for cross-domain sentiment classification. arXiv preprint arXiv:1809.00530

  27. Saito K, Ushiku Y, Harada T, Saenko K (2019) Strong-weak distribution alignment for adaptive object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6956–6965

  28. Chen X, Pan S, Chong Y (2022) Unsupervised domain adaptation for remote sensing image semantic segmentation using region and category adaptive domain discriminator. IEEE Transact Geosci Remote Sens 60:1–13

    Google Scholar 

  29. Tasar O, Happy S, Tarabalka Y, Alliez P (2020) Colormapgan: Unsupervised domain adaptation for semantic segmentation using color mapping generative adversarial networks. IEEE Transact Geosci Remote Sens 58(10):7178–7193

    Article  Google Scholar 

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

  31. Long M, Cao Z, Wang J, Jordan MI (2017) Conditional adversarial domain adaptation. arXiv preprint arXiv:1705.10667

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

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

  34. Zhu X, Pang J, Yang C, Shi J, Lin D (2019) Adapting object detectors via selective cross-domain alignment. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 687–696

  35. He Z, Zhang L (2019) Multi-adversarial faster-rcnn for unrestricted object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6668–6677

  36. Li X, Chen W, Xie D, Yang S, Yuan P, Pu S, Zhuang Y (2020) A free lunch for unsupervised domain adaptive object detection without source data. arXiv preprint arXiv:2012.05400

  37. Liu Y, Shu C, Wang J, Shen C (2020) Structured knowledge distillation for dense prediction. IEEE Transact Pattern Anal Mach Intell

  38. Passalis N, Tefas A (2018) Learning deep representations with probabilistic knowledge transfer. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 268–284

  39. Passalis N, Tzelepi M, Tefas A (2020) Probabilistic knowledge transfer for lightweight deep representation learning. IEEE Transact Neur Netw Learn Syst 32(5):2030–2039

    Article  MathSciNet  Google Scholar 

  40. Seo H, Park J, Oh S, Bennis M, Kim S-L (2020) Federated knowledge distillation. arXiv preprint arXiv:2011.02367

  41. Xie J, Shuai B, Hu J-F, Lin J, Zheng W-S (2018) Improving fast segmentation with teacher-student learning. arXiv preprint arXiv:1810.08476

  42. Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223

  43. Sakaridis C, Dai D, Van Gool L (2018) Semantic foggy scene understanding with synthetic data. Int J Comput Vision 126(9):973–992

    Article  Google Scholar 

  44. Inoue N, Furuta R, Yamasaki T, Aizawa K (2018) Cross-domain weakly-supervised object detection through progressive domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5001–5009

Download references

Acknowledgements

This work was supported by Joint Fund of Natural Science Foundation of Anhui Province in 2020 (2008085UD08), Anhui Provincial Key R &D Program (202004a05020004), Open fund of Intelligent Interconnected Systems Laboratory of Anhui Province (PA2021AKSK0107), Intelligent Networking and New Energy Vehicle Special Project of Intelligent Manufacturing Institute of HFUT (IMIWL2019003, IMIDC2019002).

Author information

Authors and Affiliations

  1. School of Computer and Information, Hefei University of Technology, Emerald Road 420, Hefei City, 230601, Anhui Province, China

    Xing Wei, Ting Bai, Yan Zhai & Yang Lu

  2. Intelligent Manufacturing Institute of Hefei University of Technology, Hefei University of Technology, Emerald Road 420, Hefei City, 230051, Anhui Province, China

    Xing Wei, Hui Luo & Chong Zhao

  3. Engineering Research Center of Safety Critical Industrial Measurement and Control Technology, Ministry of Education, Hefei City, 230009, Anhui Province, China

    Xing Wei & Yang Lu

  4. Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei City, 230031, Anhui Province, China

    Lei Chen

  5. Engineering Quality Education Center of Undergraduate School, Hefei University of Technology, Hefei City, 230601, Anhui Province, China

    Chong Zhao

Authors
  1. Xing Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ting Bai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yan Zhai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hui Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chong Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yang Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ting Bai.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wei, X., Bai, T., Zhai, Y. et al. Source-free domain adaptive object detection based on pseudo-supervised mean teacher. J Supercomput 79, 6228–6251 (2023). https://doi.org/10.1007/s11227-022-04915-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-022-04915-4

Keywords

Search

Navigation