Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation

CVPR 2019 Chen-Yu LeeTanmay BatraMohammad Haris BaigDaniel Ulbricht

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... (read more)

PDF Abstract
Task Dataset Model Metric name Metric value Global rank Compare
Unsupervised Domain Adaptation GTAV-to-Cityscapes Labels SWD mIoU 44.5 # 1
Unsupervised Domain Adaptation VisDA2017 SWD Accuracy 76.4 # 1