Who is closer: A computational method for domain gap evaluation

作者：

Highlights：

• It is an original work on domain gap evaluation.

• Proposed method can reasonably measure domain gaps.

• Proposed method is also instructive for applications on unlabeled datasets.

摘要

•It is an original work on domain gap evaluation.•Proposed method can reasonably measure domain gaps.•Proposed method is also instructive for applications on unlabeled datasets.

论文关键词：Domain gap evaluation,CNN,Domain adaptive learning

论文评审过程：Received 28 October 2020, Revised 2 August 2021, Accepted 31 August 2021, Available online 1 September 2021, Version of Record 1 October 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.108293