Abstract
We explore the use of generative modeling in unsupervised domain adaptation (UDA), where annotated real images are only available in the source domain, and pseudo images are generated in a manner that allows independent control of class (content) and nuisance variability (style). The proposed method differs from existing generative UDA models in that we explicitly disentangle the content and nuisance features at different layers of the generator network. We demonstrate the effectiveness of (pseudo)-conditional generation by showing that it improves upon baseline methods. Moreover, we outperform the previous state-of-the-art with significant margins in recently introduced multi-source domain adaptation (MSDA) tasks, achieving significant error reduction rates of \(50.27 \%\), \(89.54 \%\), \(75.35 \%\), \(27.46 \%\) and \(94.3 \%\) in all 5 tasks.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4401–4410 (2019)
Xu, R., Chen, Z., Zuo, W., Yan, J., Lin, L.: Deep cocktail network: multi-source unsupervised domain adaptation with category shift. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3964–3973 (2018)
Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. arXiv preprint arXiv:1812.01754 (2018)
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
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Cicek, S., Xu, N., Wang, Z., Jin, H., Soatto, S. (2020). Disentangled Image Generation for Unsupervised Domain Adaptation. In: Bartoli, A., Fusiello, A. (eds) Computer Vision – ECCV 2020 Workshops. ECCV 2020. Lecture Notes in Computer Science(), vol 12535. Springer, Cham. https://doi.org/10.1007/978-3-030-66415-2_44
Download citation
DOI: https://doi.org/10.1007/978-3-030-66415-2_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66414-5
Online ISBN: 978-3-030-66415-2
eBook Packages: Computer ScienceComputer Science (R0)