Scale variance minimization for unsupervised domain adaptation in image segmentation

作者：

Highlights：

• Scale-invariance constraint preserves semantic structures of images.

• Scale variance minimization ensures optimal unsupervised domain adaptation.

• Proposed method is complementary to most existing domain adaptation techniques.

• Superior performance has been achieved comparing with the state-of-the-art.

摘要

•Scale-invariance constraint preserves semantic structures of images.•Scale variance minimization ensures optimal unsupervised domain adaptation.•Proposed method is complementary to most existing domain adaptation techniques.•Superior performance has been achieved comparing with the state-of-the-art.

论文关键词：Unsupervised domain adaptation,Image segmentation,Semantic structure,Variance minimization,Adversarial learning

论文评审过程：Received 18 August 2020, Revised 8 October 2020, Accepted 21 November 2020, Available online 5 December 2020, Version of Record 14 December 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107764