Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation
Abstract
Recent works on domain adaptation exploit adversarial training to obtain domain-invariant feature representations from the joint learning of feature extractor and domain discriminator networks. However, domain adversarial methods render suboptimal performances since they attempt to match the distributions among the domains without considering the task at hand. We propose Drop to Adapt (DTA), which leverages adversarial dropout to learn strongly discriminative features by enforcing the cluster assumption. Accordingly, we design objective functions to support robust domain adaptation. We demonstrate efficacy of the proposed method on various experiments and achieve consistent improvements in both image classification and semantic segmentation tasks. Our source code is available at https://github.com/postBG/DTA.pytorch.
Cite
Text
Lee et al. "Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. doi:10.1109/ICCV.2019.00018Markdown
[Lee et al. "Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation." Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019.](https://mlanthology.org/iccv/2019/lee2019iccv-drop/) doi:10.1109/ICCV.2019.00018BibTeX
@inproceedings{lee2019iccv-drop,
title = {{Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation}},
author = {Lee, Seungmin and Kim, Dongwan and Kim, Namil and Jeong, Seong-Gyun},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
year = {2019},
doi = {10.1109/ICCV.2019.00018},
url = {https://mlanthology.org/iccv/2019/lee2019iccv-drop/}
}