Abstract
Source-Free domain adaptive Object Detection (SFOD) is a promising strategy for deploying trained detectors to new, unlabeled domains without accessing source data, addressing significant concerns around data privacy and efficiency. Most SFOD methods leverage a Mean-Teacher (MT) self-training paradigm relying heavily on High-confidence Pseudo Labels (HPL). However, these HPL often overlook small instances that undergo significant appearance changes with domain shifts. Additionally, HPL ignore instances with low confidence due to the scarcity of training samples, resulting in biased adaptation toward familiar instances from the source domain. To address this limitation, we introduce the Low-confidence Pseudo Label Distillation (LPLD) loss within the Mean-Teacher based SFOD framework. This novel approach is designed to leverage the proposals from Region Proposal Network (RPN), which potentially encompasses hard-to-detect objects in unfamiliar domains. Initially, we extract HPL using a standard pseudo-labeling technique and mine a set of Low-confidence Pseudo Labels (LPL) from proposals generated by RPN, leaving those that do not overlap significantly with HPL. These LPL are further refined by leveraging class-relation information and reducing the effect of inherent noise for the LPLD loss calculation. Furthermore, we use feature distance to adaptively weight the LPLD loss to focus on LPL containing a larger foreground area. Our method outperforms previous SFOD methods on four cross-domain object detection benchmarks. Extensive experiments demonstrate that our LPLD loss leads to effective adaptation by reducing false negatives and facilitating the use of domain-invariant knowledge from the source model. Code is available at https://github.com/junia3/LPLD.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Arruda, V.F., et al.: Cross-domain car detection using unsupervised image-to-image translation: from day to night. In: IJCNN (2019)
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13
Chen, C., et al.: Progressive feature alignment for unsupervised domain adaptation. In: CVPR (2019)
Chen, C., Zheng, Z., Ding, X., Huang, Y., Dou, Q.: Harmonizing transferability and discriminability for adapting object detectors. In: CVPR (2020)
Chen, M., et al.: Learning domain adaptive object detection with probabilistic teacher. In: ICML (2022)
Chen, W., Lin, L., Yang, S., Xie, D., Pu, S., Zhuang, Y.: Self-supervised noisy label learning for source-free unsupervised domain adaptation. In: IROS (2022)
Chen, Y., Li, W., Sakaridis, C., Dai, D., Van Gool, L.: Domain adaptive faster R-CNN for object detection in the wild. In: CVPR (2018)
Chen, Z., Wang, Z., Zhang, Y.: Exploiting low-confidence pseudo-labels for source-free object detection. In: ACM (2023)
Chu, Q., Li, S., Chen, G., Li, K., Li, X.: Adversarial alignment for source free object detection. In: AAAI (2023)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)
Deng, J., Li, W., Chen, Y., Duan, L.: Unbiased mean teacher for cross-domain object detection. In: CVPR (2021)
Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL visual object classes challenge: a retrospective. IJCV 111, 98–136 (2015)
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)
Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)
He, Z., Zhang, L.: Multi-adversarial faster-RCNN for unrestricted object detection. In: ICCV (2019)
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
Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: ICML (2018)
Huang, J., Guan, D., Xiao, A., Lu, S.: Model adaptation: historical contrastive learning for unsupervised domain adaptation without source data. In: NeurIPS (2021)
Inoue, N., Furuta, R., Yamasaki, T., Aizawa, K.: Cross-domain weakly-supervised object detection through progressive domain adaptation. In: CVPR (2018)
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: ICRA (2017)
Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: CVPR (2019)
Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)
Khodabandeh, M., Vahdat, A., Ranjbar, M., Macready, W.G.: A robust learning approach to domain adaptive object detection. In: ICCV (2019)
Kim, S., Choi, J., Kim, T., Kim, C.: Self-training and adversarial background regularization for unsupervised domain adaptive one-stage object detection. In: ICCV (2019)
Kim, T., Jeong, M., Kim, S., Choi, S., Kim, C.: Diversify and match: a domain adaptive representation learning paradigm for object detection. In: CVPR (2019)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Kundu, J.N., Venkat, N., Babu, R.V., et al.: Universal source-free domain adaptation. In: CVPR (2020)
Lee, D.H., et al.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML (2013)
Li, S., Ye, M., Zhu, X., Zhou, L., Xiong, L.: Source-free object detection by learning to overlook domain style. In: CVPR (2022)
Li, X., et al.: A free lunch for unsupervised domain adaptive object detection without source data. In: AAAI (2021)
Liang, J., Hu, D., Feng, J.: Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation. In: ICML (2020)
Lin, T.Y., Dollár, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)
Liu, H., Wang, J., Long, M.: Cycle self-training for domain adaptation. In: NeurIPS (2021)
Liu, Q., Lin, L., Shen, Z., Yang, Z.: Periodically exchange teacher-student for source-free object detection. In: ICCV (2023)
Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: NeurIPS (2016)
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: AISTATS (2017)
Morerio, P., Volpi, R., Ragonesi, R., Murino, V.: Generative pseudo-label refinement for unsupervised domain adaptation. In: WACV (2020)
Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., Kim, K.: Image to image translation for domain adaptation. In: CVPR (2018)
Pinheiro, P.O.: Unsupervised domain adaptation with similarity learning. In: CVPR (2018)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: CVPR (2016)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)
Rodriguez, A.L., Mikolajczyk, K.: Domain adaptation for object detection via style consistency. In: BMVC (2019)
Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Strong-weak distribution alignment for adaptive object detection. In: CVPR (2019)
Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: CVPR (2018)
Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. IJCV 126, 973–992 (2018)
Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: S &P (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)
Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: NeurIPS (2020)
Soviany, P., Ionescu, R.T., Rota, P., Sebe, N.: Curriculum self-paced learning for cross-domain object detection. CVIU 204, 103166 (2021)
Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: NeurIPS (2017)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)
Vandeghen, R., Louppe, G., Van Droogenbroeck, M.: Adaptive self-training for object detection. In: ICCV (2023)
Vibashan, V., Oza, P., Patel, V.M.: Instance relation graph guided source-free domain adaptive object detection. In: CVPR (2023)
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 (2021)
Wang, Q., Breckon, T.: Unsupervised domain adaptation via structured prediction based selective pseudo-labeling. In: AAAI (2020)
Xu, C.D., Zhao, X.R., Jin, X., Wei, X.S.: Exploring categorical regularization for domain adaptive object detection. In: CVPR (2020)
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
Zhuang, C., Han, X., Huang, W., Scott, M.: iFAN: image-instance full alignment networks for adaptive object detection. In: AAAI (2020)
Zou, Y., Yu, Z., Liu, X., Kumar, B., Wang, J.: Confidence regularized self-training. In: ICCV (2019)
Acknowledgements
This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF2021R1A2C2006703), and partly supported by the Yonsei Signature Research Cluster Program of 2024 (2024-22-0161).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yoon, I., Kwon, H., Kim, J., Park, J., Jang, H., Sohn, K. (2025). Enhancing Source-Free Domain Adaptive Object Detection with Low-Confidence Pseudo Label Distillation. 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 15142. Springer, Cham. https://doi.org/10.1007/978-3-031-72907-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-72907-2_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-72906-5
Online ISBN: 978-3-031-72907-2
eBook Packages: Computer ScienceComputer Science (R0)