Feature concatenation for adversarial domain adaptation

作者：

Highlights：

• The proposed adversarial domain adaptation method enhances the discriminability.

• The proposed method represents a sample by concatenating two different views.

• The consistency and complementarity of two views are guaranteed in both domains.

• The model is optimized in an adversarial way.

摘要

•The proposed adversarial domain adaptation method enhances the discriminability.•The proposed method represents a sample by concatenating two different views.•The consistency and complementarity of two views are guaranteed in both domains.•The model is optimized in an adversarial way.

论文关键词：Domain adaptation,Feature concatenation,Adversarial learning

论文评审过程：Received 9 August 2020, Revised 26 November 2020, Accepted 8 December 2020, Available online 13 December 2020, Version of Record 24 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114490