English

Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

Computer Vision and Pattern Recognition 2019-03-12 v1 Machine Learning Machine Learning

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.

Keywords

Cite

@article{arxiv.1903.04064,
  title  = {Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation},
  author = {Chen-Yu Lee and Tanmay Batra and Mohammad Haris Baig and Daniel Ulbricht},
  journal= {arXiv preprint arXiv:1903.04064},
  year   = {2019}
}

Comments

Accepted at CVPR 2019

R2 v1 2026-06-23T08:03:43.143Z