Correlation-aware adversarial domain adaptation and generalization

作者：

Highlights：

• We propose a new deep domain adaptation (DA) framework.

• We further extend the proposed DA framework on deep domain generalization (DG) scenarios.

• The proposed method exceeds state-of-the-art performance on both DA and DG scenarios.

• Cross-domain testing confirms the suitability for real-world applications.

摘要

•We propose a new deep domain adaptation (DA) framework.•We further extend the proposed DA framework on deep domain generalization (DG) scenarios.•The proposed method exceeds state-of-the-art performance on both DA and DG scenarios.•Cross-domain testing confirms the suitability for real-world applications.

论文关键词：Domain adaptation,Domain generalization,Correlation-alignment,Adversarial learning

论文评审过程：Received 30 November 2018, Revised 23 October 2019, Accepted 21 November 2019, Available online 28 November 2019, Version of Record 13 May 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107124