Skip to main content

Advertisement

Springer Nature Link
Log in

Proposal-level reliable feature-guided contrastive learning for SFOD

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

Abstract

Domain adaptive object detection (DAOD) is an effective approach to solving the domain shift problem, which aims to improve the generalization ability on the target domain through joint training with labeled source domain and unlabeled target domain data. However, in the real world, the source domain is often inaccessible due to privacy, legal, and regulatory reasons. Source-free object detection (SFOD) adapts a well-trained source domain object detector to the target domain without needing access to source domain data. Most existing SFOD methods are based on a self-training framework (such as the teacher–student framework), where the teacher model guides the student model’s training by setting a confidence threshold to filter out unreliable pseudo-labels. However, this may lead to the loss of semantic information in the target domain, resulting in suboptimal model performance. Therefore, in this paper, we propose a contrastive learning framework guided by proposal-level reliable feature guidance. Specifically, we first build a general self-training framework based on Faster-RCNN. Then, we introduce a novel proposal-level pseudo-label annotation and filtering method (PAF), improving the annotation and filtering of pseudo-labels and obtaining proposal-level reliable features. Next, we design reliable feature banks to categorize and store reliable proposal features. Finally, we propose classification contrastive learning (CCL) and bounding box contrastive learning (BCL) to further extract semantic information from reliable proposal features, learning the lost semantic information in the target domain. Extensive experiments on seven benchmark datasets demonstrate the effectiveness of our 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
$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

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data availability

No datasets were generated or analysed during the current study

References

  1. Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Adv neural inf process syst 28:1137–1149

    Google Scholar 

  2. Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, et al (2022) Yolov6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976

  3. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You Only Look Once: Unified, Real-time Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788

  4. Torralba A, Efros AA (2011) Unbiased Iook at Dataset Bias. In: CVPR 2011, pp. 1521–1528. IEEE

  5. Lin Y-E, Liu E, Liang X, Chen M, Yan X (2024) Global-local bi-alignment for purer unsupervised domain adaptation. J Supercomput 80(10):14925–14952

    Article  Google Scholar 

  6. Zhang M, Li X, Wu F (2023) Moka-ada: adversarial domain adaptation with model-oriented knowledge adaptation for cross-domain sentiment analysis. J Supercomput 79(12):13724–13743

    Article  Google Scholar 

  7. Hsu C-C, Tsai Y-H, Lin Y-Y, Yang M-H (2020) Every pixel matters: Center-aware Feature Alignment for Domain Adaptive Object Detector. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IX 16, pp. 733–748. Springer

  8. 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

  9. 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

  10. 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

  11. 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

  12. Cao S, Joshi D, Gui L-Y, Wang Y-X (2023) Contrastive Mean Teacher for Domain Adaptive Object Detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 23839–23848

  13. Li W, Liu X, Yuan Y (2023) Sigma++: Improved semantic-complete graph matching for domain adaptive object detection. IEEE Trans Pattern Anal Mach Intell 45(7):9022–9040

    Google Scholar 

  14. Vs V, Gupta V, Oza P, Sindagi VA, Patel VM (2021) 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

  15. Chen T, Kornblith S, Norouzi M, Hinton G (2020) A Simple Framework for Contrastive Learning of Visual Representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR

  16. Johnson-Roberson M, Barto C, Mehta R, Sridhar SN, Rosaen K, Vasudevan R (2016) Driving in the Matrix: Can Virtual Worlds Replace Human-generated Annotations for Real World Tasks? arXiv preprint arXiv:1610.01983

  17. He K, Zhang X, Ren S, Sun J (2016) Deep Residual Learning for Image Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778

  18. Zhang S, Zhang L, Li G, Li P, Liu Z (2023) Multi-prototype guided source-free domain adaptive object detection for autonomous driving. IEEE Trans Intell Veh 9:1589–1601

    Article  Google Scholar 

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

    Article  Google Scholar 

  20. Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int j comput vis 88:303–338

    Article  Google Scholar 

  21. 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

  22. Li S, Ye M, Zhu X, Zhou L, Xiong L (2022) 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

  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. VS V, Oza P, Patel VM (2023) Instance Relation Graph Guided Source-free Domain Adaptive Object Detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3520–3530

  25. Chu Q, Li S, Chen G, Li K, Li X (2023) Adversarial Alignment for Source Free Object Detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 452–460

  26. Huang J, Guan D, Xiao A, Lu S (2021) Model adaptation: historical contrastive learning for unsupervised domain adaptation without source data. Adv neural inf process syst 34:3635–3649

    Google Scholar 

  27. Vs V, Oza P, Sindagi VA, Patel VM (2022) Mixture of Teacher Experts for Source-free Domain Adaptive Object Detection. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 3606–3610. IEEE

  28. VS V, Oza P, Patel VM (2023) Towards Online Domain Adaptive Object Detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 478–488

  29. Tarvainen A, Valpola H (2017) Mean Teachers are Better Role Models: Weight-averaged Consistency Targets Improve Semi-supervised Deep Learning Results. Adv neural inf process syst 30

  30. Gal Y, Ghahramani Z (2016) Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In: International Conference on Machine Learning, pp. 1050–1059. PMLR

  31. Hsu H-K, Yao C-H, Tsai Y-H, Hung W-C, Tseng H-Y, Singh M, Yang M-H (2020) Progressive Domain Adaptation for Object Detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 749–757

  32. Zhu, J-Y, Park T, Isola P, Efros AA (2017) Unpaired Image-to-Image Translation Using Cycle-consistent Adversarial Networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2223–2232

  33. Li X, Chen W, Xie D, Yang S, Yuan P, Pu S, Zhuang Y (2021) 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

  34. He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum Contrast for Unsupervised Visual Representation Learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729–9738

  35. Ouyang F, Shen B (2024) A mutual mean teacher framework for cross-domain aspect-based sentiment analysis. J Supercomput 80(7):9073–9095

    Article  Google Scholar 

  36. Munir MA, Khan MH, Sarfraz M, Ali M (2021) Ssal: Synergizing between self-training and adversarial learning for domain adaptive object detection. Adva Neural Inf Process Syst 34:22770–22782

    Google Scholar 

  37. 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

  38. 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

  39. He Z, Zhang L (2020) Domain Adaptive Object Detection Via Asymmetric Tri-way Faster-rcnn. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIV 16, pp. 309–324 Springer

  40. Chen C, Zheng Z, Ding X, Huang Y, Dou Q (2020) Harmonizing Transferability and Discriminability for Adapting Object Detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8869–8878

  41. Chen C, Zheng Z, Huang Y, Ding X, Yu Y (2021) I3net: Implicit Instance-invariant Network for Adapting One-stage Object Detectors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12576–12585

  42. Geiger A, Lenz P, Stiller C, Urtasun R (2013) Vision meets robotics: The kitti dataset. Int J Robot Res 32(11):1231–1237

    Article  Google Scholar 

  43. Shen Z, Maheshwari H, Yao W, Savvides M (2019) Scl: Towards Accurate Domain Adaptive Object Detection Via Gradient Detach Based Stacked Complementary Losses. arXiv preprint arXiv:1911.02559

  44. Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J mach learn res 9(11):2579–2605

    Google Scholar 

Download references

Acknowledgements

This work was supported by Key Laboratory of AI and Information Processing, Education Department of Guangxi Zhuang Autonomous Region (Hechi University) (2024GXZDSY007), Hefei Natural Science Foundation Project (202308, 202316), Anhui Province Science and Technology Innovation Project (202423k09020003).

Funding

This work was funded by Key Laboratory of AI and Information Processing, Education Department of Guangxi Zhuang Autonomous Region (Hechi University)(2024GXZDSY007), Hefei Natural Science Foundation Project (202308, 202316), Anhui Province Science and Technology Innovation Project (202423k09020003).

Author information

Author notes

  1. Xing Wei, Jiong Xia, Jun Chen, Zhen Wei, Chong Zhao, Fan Yang and Yang Lu have contributed equally.

Authors and Affiliations

  1. School of Computer and Information, Hefei University of Technology, Hefei, 230601, China

    Xing Wei, Jiong Xia, Cang Liu, Zhen Wei, Fan Yang & Yang Lu

  2. Department of Artificial Intelligence and Manufacturing, Hechi University, Hechi, 547000, China

    Qi-wen He & Jun Chen

  3. Key Laboratory of AI and Information Processing (Hechi University), Education Department of Guangxi Zhuang Autonomous Region, Hechi, 546300, Guangxi, China

    Qi-wen He & Jun Chen

  4. Anhui Mine IOT and Security Monitoring Technology Key Laboratory, Hefei, 230088, China

    Fan Yang

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

    Chong Zhao

Authors
  1. Xing Wei
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Jiong Xia
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Cang Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Qi-wen He
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Jun Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Zhen Wei
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Chong Zhao
    View author publications

    You can also search for this author inPubMed Google Scholar

  8. Fan Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  9. Yang Lu
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

X.J. C. wrote the main manuscript text, Q.J. Z.prepared figures and C.F. completed the experiment.

Corresponding authors

Correspondence to Cang Liu or Qi-wen He.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

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., Xia, J., Liu, C. et al. Proposal-level reliable feature-guided contrastive learning for SFOD. J Supercomput 81, 256 (2025). https://doi.org/10.1007/s11227-024-06773-8

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-024-06773-8

Keywords