Abstract
Unsupervised domain adaptation has drawn sustained attentions in medical image segmentation by transferring knowledge from labeled source data to unlabeled target domain. However, most existing approaches assume the source data are collected from a single client, which cannot be successfully applied to explore complementary transferable knowledge from multiple source domains with large distribution discrepancy. Moreover, they require access to source data during training, which is inefficient and unpractical due to privacy preservation and memory storage. To address these challenges, we study a novel and practical problem, named multi-source model adaptation (MSMA), which aims to transfer multiple source models to the unlabeled target domain without any source data. Since no target label and source data is provided to evaluate the transferability of each source model or domain gap between the source and the target domain, we may encounter negative transfer by those less related source domains, thus hurting target performance. To solve this problem, we propose a transferability-guided model adaptation (TGMA) framework to eliminate negative transfer. Specifically, 1) A label-free transferability metric (LFTM) is designed to evaluate transferability of source models without target annotations for the first time. 2) Based on the designed metric, we compute instance-level transferability matrix (ITM) for target pseudo label correction and domain-level transferability matrix (DTM) to achieve model selection for better target model initialization. Extensive experiments on multi-site prostate segmentation dataset demonstrate the superiority of our framework.
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
Ahmed, S.M., Raychaudhuri, D.S., Paul, S., Oymak, S., Roy-Chowdhury, A.K.: Unsupervised multi-source domain adaptation without access to source data. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10103–10112 (2021)
Bateson, M., Kervadec, H., Dolz, J., Lombaert, H., Ayed, I.B.: Source-free domain adaptation for image segmentation. Med. Image Anal. 82, 102617 (2022)
Dong, J., Fang, Z., Liu, A., Sun, G., Liu, T.: Confident anchor-induced multi-source free domain adaptation. Adv. Neural. Inf. Process. Syst. 34, 2848–2860 (2021)
Feng, H., et al.: KD3A: Unsupervised multi-source decentralized domain adaptation via knowledge distillation. In: ICML, pp. 3274–3283 (2021)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2030–2096 (2016)
Liang, J., Hu, D., Feng, J.: 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 (2020)
Liang, J., Hu, D., Feng, J., He, R.: Dine: Domain adaptation from single and multiple black-box predictors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8003–8013 (2022)
Liu, X., Yuan, Y.: A source-free domain adaptive polyp detection framework with style diversification flow. IEEE Trans. Med. Imaging 41(7), 1897–1908 (2022)
Liu, Y., Zhang, W., Wang, J.: Source-free domain adaptation for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1215–1224 (2021)
Nguyen, C., Hassner, T., Seeger, M., Archambeau, C.: Leep: A new measure to evaluate transferability of learned representations. In: International Conference on Machine Learning, pp. 7294–7305. PMLR (2020)
Ren, C.X., Liu, Y.H., Zhang, X.W., Huang, K.K.: Multi-source unsupervised domain adaptation via pseudo target domain. IEEE Trans. Image Process. 31, 2122–2135 (2022)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Tran, A.T., Nguyen, C.V., Hassner, T.: Transferability and hardness of supervised classification tasks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1395–1405 (2019)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 7167–7176 (2017)
Wang, J., Jin, Y., Wang, L.: Personalizing federated medical image segmentation via local calibration. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XXI. pp. 456–472. Springer (2022). https://doi.org/10.1007/978-3-031-19803-8_27
Yang, C., Guo, X., Chen, Z., Yuan, Y.: Source free domain adaptation for medical image segmentation with Fourier style mining. Med. Image Anal. 79, 102457 (2022)
Yang, C., Guo, X., Zhu, M., Ibragimov, B., Yuan, Y.: Mutual-prototype adaptation for cross-domain polyp segmentation. IEEE J. Biomed. Health Inform. 25(10), 3886–3897 (2021). https://doi.org/10.1109/JBHI.2021.3077271
Yang, S., van de Weijer, J., Herranz, L., Jui, S., et al.: Exploiting the intrinsic neighborhood structure for source-free domain adaptation. Adv. Neural. Inf. Process. Syst. 34, 29393–29405 (2021)
Yao, Y., Li, X., Zhang, Y., Ye, Y.: Multisource heterogeneous domain adaptation with conditional weighting adversarial network. IEEE Trans. Neural Netw. Learn. Syst. (2021)
You, K., Liu, Y., Wang, J., Long, M.: Logme: practical assessment of pre-trained models for transfer learning. In: International Conference on Machine Learning, pp. 12133–12143. PMLR (2021)
Zhao, S., et al.: Multi-source distilling domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 34, pp. 12975–12983 (2020)
Acknowledgements
This work was supported by National Natural Science Foundation of China 62001410, Hong Kong Research Grants Council (RGC) Early Career Scheme grant 21207420, General Research Fund 11211221.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yang, C., Liu, Y., Yuan, Y. (2023). Transferability-Guided Multi-source Model Adaptation for Medical Image Segmentation. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14221. Springer, Cham. https://doi.org/10.1007/978-3-031-43895-0_66
Download citation
DOI: https://doi.org/10.1007/978-3-031-43895-0_66
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43894-3
Online ISBN: 978-3-031-43895-0
eBook Packages: Computer ScienceComputer Science (R0)
