Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

Chen-Yu Lee, Tanmay Batra, Mohammad Haris Baig, Daniel Ulbricht; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10285-10295

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.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Lee_2019_CVPR,
author = {Lee, Chen-Yu and Batra, Tanmay and Baig, Mohammad Haris and Ulbricht, Daniel},
title = {Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}