Spatial Class Distribution Shift in Unsupervised Domain Adaptation: Local Alignment Comes to Rescue

Safa Cicek, Ning Xu, Zhaowen Wang, Hailin Jin, Stefano Soatto

Abstract: We propose a method for semantic segmentation in the unsupervised domain adaptation (UDA) setting. We particularly examine the domain gap between spatial-class distributions and propose to align the local distributions of the segmentation predictions. Despite its simplicity, the proposed method achieves state-of-the-art results in UDA segmentation benchmarks.