Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation
Abstract
In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity between the outputs of task-specific classifiers. It provides a geometrically meaningful guidance to detect target samples that are far from the support of the source and enables efficient distribution alignment in an end-to-end trainable fashion. In the experiments, we validate the effectiveness and genericness of our method on digit and sign recognition, image classification, semantic segmentation, and object detection.
Cite
Text
Lee et al. "Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.01053Markdown
[Lee et al. "Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/lee2019cvpr-sliced/) doi:10.1109/CVPR.2019.01053BibTeX
@inproceedings{lee2019cvpr-sliced,
title = {{Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation}},
author = {Lee, Chen-Yu and Batra, Tanmay and Baig, Mohammad Haris and Ulbricht, Daniel},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.01053},
url = {https://mlanthology.org/cvpr/2019/lee2019cvpr-sliced/}
}