Skip to main content
Springer Nature Link
Log in

Revisiting Domain-Adaptive Object Detection in Adverse Weather by the Generation and Composition of High-Quality Pseudo-labels

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15094))

Included in the following conference series:

  • 516 Accesses

Abstract

Due to data collection challenges, the mean-teacher learning paradigm has emerged as a critical approach for cross-domain object detection, especially in adverse weather conditions. Despite significant progress, existing methods are still plagued by low-quality pseudo-labels in degraded images. This paper proposes a generation-composition paradigm training framework that includes the tiny-object-friendly loss, i.e., IAoU loss with a joint-filtering and student-aware strategy to improve pseudo-labels generation quality and refine the filtering scheme. Specifically, in the generation phase of pseudo-labels, we observe that bounding box regression is essential for feature alignment and develop the IAoU loss to enhance the precision of bounding box regression, further facilitating subsequent feature alignment. We also find that selecting bounding boxes based solely on classification confidence performs poorly in cross-domain noisy image scenes. Moreover, relying exclusively on predictions from the teacher model could cause the student model to collapse. Accordingly, in the composition phase, we introduce the mean-teacher model with a joint-filtering and student-aware strategy combining classification and regression thresholds from both the student and the teacher models. Our extensive experiments, conducted on synthetic and real-world adverse weather datasets, clearly demonstrate that the proposed method surpasses state-of-the-art benchmarks across all scenarios, particularly achieving a 12.4\(\%\) improvement of mAP, i.e., Cityscapes to RTTS. Our code will be available at https://github.com/iu110/GCHQ/.

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

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Balakrishna, S., Mustapha, A.A.: Progress in multi-object detection models: a comprehensive survey. Multim. Tools Appl. 82(15), 22405–22439 (2023)

    Article  Google Scholar 

  2. Cao, S., Joshi, D., Gui, L., Wang, Y.: Contrastive mean teacher for domain adaptive object detectors. In: CVPR, pp. 23839–23848 (2023)

    Google Scholar 

  3. Chen, C., Zheng, Z., Ding, X., Huang, Y., Dou, Q.: Harmonizing transferability and discriminability for adapting object detectors. In: CVPR, pp. 8869–8878 (2020)

    Google Scholar 

  4. Chen, C., Zheng, Z., Ding, X., Huang, Y., Dou, Q.: Harmonizing transferability and discriminability for adapting object detectors. In: CVPR, pp. 8866–8875 (2020)

    Google Scholar 

  5. Chen, M., et al.: Learning domain adaptive object detection with probabilistic teacher. In: ICML, vol. 162, pp. 3040–3055 (2022)

    Google Scholar 

  6. Chen, X., Li, H., Li, M., Pan, J.: Learning a sparse transformer network for effective image deraining. In: CVPR, pp. 5896–5905 (2023)

    Google Scholar 

  7. Chen, Y., Jhong, S., Hsia, C.: Roadside unit-based unknown object detection in adverse weather conditions for smart internet of vehicles. ACM Trans. Manag. Inf. Syst. 13(4), 47:1–47:21 (2022)

    Google Scholar 

  8. Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster r-cnn for object detection in the wild. In: CVPR, pp. 3339–3348 (2018)

    Google Scholar 

  9. Choi, J., Chun, D., Kim, H., Lee, H.: Gaussian yolov3: An accurate and fast object detector using localization uncertainty for autonomous driving. In: ICCV, pp. 502–511 (2019)

    Google Scholar 

  10. Deng, J., Li, W., Chen, Y., Duan, L.: Unbiased mean teacher for cross-domain object detection. In: CVPR, pp. 4091–4101 (2021)

    Google Scholar 

  11. Fu, X., Huang, J., Zeng, D., Huang, Y., Ding, X., Paisley, J.W.: Removing rain from single images via a deep detail network. In: CVPR,pp. 1715–1723 (2017)

    Google Scholar 

  12. Hahner, M., Dai, D., Sakaridis, C., Zaech, J., Gool, L.V.: Semantic understanding of foggy scenes with purely synthetic data. In: ITSC, pp. 3675–3681 (2019)

    Google Scholar 

  13. He, M., et al.: Cross domain object detection by target-perceived dual branch distillation. In: CVPR, pp. 9560–9570 (2022)

    Google Scholar 

  14. 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 

  15. Hnewa, M., Radha, H.: Multiscale domain adaptive yolo for cross-domain object detection. In: ICIP, pp. 3323–3327 (2021)

    Google Scholar 

  16. Hsu, H.K., et al.: Progressive domain adaptation for object detection. In: WACV, pp. 738–746 (2019). https://api.semanticscholar.org/CorpusID:198167281

  17. Huang, S.C., Le, T.H., Jaw, D.W.: Dsnet: joint semantic learning for object detection in inclement weather conditions. IEEE Trans. Pattern Anal. Mach. Intell. 43(8) (2021)

    Google Scholar 

  18. Inoue, N., Furuta, R., Yamasaki, T., Aizawa, K.: Cross-domain weakly-supervised object detection through progressive domain adaptation. In: CVPR, pp. 5001–5009. Computer Vision Foundation/IEEE Computer Society (2018)

    Google Scholar 

  19. Kalwar, S., Patel, D., Aanegola, A., Konda, K.R., Garg, S., Krishna, K.M.: Gdip: gated differentiable image processing for object detection in adverse conditions. In: ICRA, pp. 7083–7089 (2023)

    Google Scholar 

  20. Khodabandeh, M., Vahdat, A., Ranjbar, M., Macready, W.G.: A robust learning approach to domain adaptive object detection. CoRR abs/ arXiv: 1904.02361 (2019)

  21. Kim, T., Jeong, M., Kim, S., Choi, S., Kim, C.: Diversify and match: a domain adaptive representation learning paradigm for object detection. In: CVPR, pp. 12456–12465. Computer Vision Foundation / IEEE (2019)

    Google Scholar 

  22. Li, W., Liu, X., Yuan, Y.: SIGMA++: improved semantic-complete graph matching for domain adaptive object detection. TPAMI 45(7), 9022–9040 (2023)

    Google Scholar 

  23. Li, Y., et al.: Cross-domain adaptive teacher for object detection. In: CVPR, pp. 7571–7580 (2022)

    Google Scholar 

  24. Lin, W., Chu, J., Leng, L., Miao, J., Wang, L.: Feature disentanglement in one-stage object detection. Pattern Recognit. 145, 109878 (2024)

    Article  Google Scholar 

  25. Liu, W., Ren, G., Yu, R., Guo, S., Zhu, J., Zhang, L.: Image-adaptive yolo for object detection in adverse weather conditions. In: AAAI, vol. 36, pp. 1792–1800 (2022)

    Google Scholar 

  26. Mattolin, G., Zanella, L., Ricci, E., Wang, Y.: Confmix: unsupervised domain adaptation for object detection via confidence-based mixing. In: WACV, pp. 423–433 (2023)

    Google Scholar 

  27. Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: CVPR, pp. 4500–4509 (2018)

    Google Scholar 

  28. Panagiotakopoulos, T., Dovesi, P.L., Härenstam-Nielsen, L., Poggi, M.: Online domain adaptation for semantic segmentation in ever-changing conditions. In: ECCV, vol. 13694, pp. 128–146 (2022). https://doi.org/10.1007/978-3-031-19830-4_8

  29. Park, T., Efros, A.A., Zhang, R., Zhu, J.-Y.: Contrastive learning for unpaired image-to-image translation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 319–345. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58545-7_19

    Chapter  Google Scholar 

  30. Qiu, Z., Zheng, P., Tao, X., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212–3232 (2019)

    Article  Google Scholar 

  31. Rodriguez, A.L., Mikolajczyk, K.: Domain adaptation for object detection via style consistency. arXiv preprint arXiv:1911.10033 (2019)

  32. Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: CVPR, pp. 6956–6965 (2019)

    Google Scholar 

  33. Siliang, M., Yong, X.: Mpdiou: a loss for efficient and accurate bounding box regression. arXiv preprint arXiv:2307.07662 (2023)

  34. Sindagi, V.A., Oza, P., Yasarla, R., Patel, V.M.: Prior-based domain adaptive object detection for hazy and rainy conditions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 763–780. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58568-6_45

    Chapter  Google Scholar 

  35. Tarvainen, A., Valpola, H.: Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: ICLR (2017)

    Google Scholar 

  36. 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: CVPR, pp. 4516–4526 (2021)

    Google Scholar 

  37. Wang, L., et al.: Dual multiscale mean teacher network for semi-supervised infection segmentation in chest CT volume for COVID-19. IEEE Trans. Cybern. 53(10), 6363–6375 (2023)

    Article  Google Scholar 

  38. Wang, L., Qin, H., Zhou, X., Lu, X., Zhang, F.: R-yolo: a robust object detector in adverse weather. IEEE Trans. Instrum. Meas. 72, 1–11 (2022)

    Google Scholar 

  39. Song, Y.-Z., Rui Tam, Z., Chen, H.-J., Lu, H.-H., Shuai, H.-H.: Character-preserving coherent story visualization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 18–33. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58520-4_2

    Chapter  Google Scholar 

  40. Wang, Y., et al.: TogetherNet: bridging image restoration and object detection together via dynamic enhancement learning. Comput. Graph. Forum (2022)

    Google Scholar 

  41. Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., Li, H.: Uformer: a general u-shaped transformer for image restoration. In: CVPR, pp. 17662–17672 (2022)

    Google Scholar 

  42. Wu, R., Duan, Z., Guo, C., Chai, Z., Li, C.: RIDCP: revitalizing real image dehazing via high-quality codebook priors. In: CVPR, pp. 22282–22291 (2023)

    Google Scholar 

  43. Xia, Z., Yan, C., Wei, S., Hong, G., Ping, Y.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257–276 (2023)

    Article  Google Scholar 

  44. Xiong, F., Tian, J., Hao, Z., He, Y., Ren, X.: SCMT: self-correction mean teacher for semi-supervised object detection. In: IJCAI, pp. 1488–1494 (2022)

    Google Scholar 

  45. Xu, B., Chen, M., Guan, W., Hu, L.: Efficient teacher: semi-supervised object detection for yolov5. arXiv preprint arXiv abs/2302.07577 (2023)

    Google Scholar 

  46. Xu, C., Zhao, X., Jin, X., Wei, X.: Exploring categorical regularization for domain adaptive object detection. In: CVPR, pp. 11721–11730 (2020)

    Google Scholar 

  47. Xu, X., Wang, R., Lu, J.: Low-light image enhancement via structure modeling and guidance. In: CVPR, pp. 9893–9903 (2023)

    Google Scholar 

  48. Yang, Q., Wei, X., Wang, B., Hua, X., Zhang, L.: Interactive self-training with mean teachers for semi-supervised object detection. In: CVPR, pp. 5941–5950 (2021)

    Google Scholar 

  49. Yasarla, R., Priebe, C.E., Patel, V.M.: ART-SS: an adaptive rejection technique for semi-supervised restoration for adverse weather-affected images. In: ECCV, vol. 13678, pp. 699–718 (2022)

    Google Scholar 

  50. Ye, T., et al.: Perceiving and modeling density for image dehazing. In: ECCV, vol. 13679, pp. 130–145 (2022)

    Google Scholar 

  51. Yoo, J., Chung, I., Kwak, N.: Unsupervised domain adaptation for one-stage object detector using offsets to bounding box. In: ECCV, vol. 13693, pp. 691–708 (2022)

    Google Scholar 

  52. Yu, H., Zheng, N., Zhou, M., Huang, J., Xiao, Z., Zhao, F.: Frequency and spatial dual guidance for image dehazing. In: ECCV, vol. 13679, pp. 181–198 (2022)

    Google Scholar 

  53. Yu, J., et al.: Mttrans: cross-domain object detection with mean teacher transformer. In: ECCV, pp. 629–645 (2022)

    Google Scholar 

  54. Zaidi, S.S.A., Ansari, M.S., Aslam, A., Kanwal, N., Asghar, M., Lee, B.: A survey of modern deep learning based object detection models. Digital Signal Process. 126, 103514 (2022)

    Article  Google Scholar 

  55. Zhang, K., et al.: Beyond monocular deraining: stereo image deraining via semantic understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 71–89. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58583-9_5

    Chapter  Google Scholar 

  56. Zhang, S., Tuo, H., Hu, J., Jing, Z.: Domain adaptive yolo for one-stage cross-domain detection. In: ACML, pp. 785–797 (2021)

    Google Scholar 

  57. Zhang, Y., Shi, Z., Zhang, Y.: Adioc loss: an auxiliary descent ioc loss function. Eng. Appl. Artif. Intell. 116, 105453 (2022)

    Article  Google Scholar 

  58. 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 

  59. Zhao, Z., et al.: Masked retraining teacher-student framework for domain adaptive object detection. In: ICCV, pp. 18993–19003 (2023)

    Google Scholar 

  60. Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: faster and better learning for bounding box regression. In: AAAI, vol. 34, pp. 12993–13000 (2020)

    Google Scholar 

  61. Zhou, H., Jiang, F., Lu, H.: SSDA-YOLO: semi-supervised domain adaptive YOLO for cross-domain object detection. Comput. Vis. Image Underst. 229, 103649 (2023)

    Article  Google Scholar 

  62. Zhou, W., Du, D., Zhang, L., Luo, T., Wu, Y.: Multi-granularity alignment domain adaptation for object detection. In: CVPR, pp. 9571–9580 (2022)

    Google Scholar 

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

    Google Scholar 

Download references

Acknowledgements

This work is supported in part by the National Natural Science Foundation of China (Project number 62101336); and in part by the Guangdong Basic and Applied Basic Research Foundation (Project number 2022A1515011301).

Author information

Authors and Affiliations

  1. School of Electronics and Information Engineering, Shenzhen University, Shenzhen, China

    Rui Zhao, Huibin Yan & Shuoyao Wang

Authors
  1. Rui Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Huibin Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shuoyao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shuoyao Wang .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1310 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

Zhao, R., Yan, H., Wang, S. (2025). Revisiting Domain-Adaptive Object Detection in Adverse Weather by the Generation and Composition of High-Quality Pseudo-labels. 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 15094. Springer, Cham. https://doi.org/10.1007/978-3-031-72764-1_16

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72764-1_16

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72763-4

  • Online ISBN: 978-3-031-72764-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics