A Two-Way alignment approach for unsupervised multi-Source domain adaptation
作者：
Highlights：
• We introduce a two-way alignment framework for unsupervised multisource domain adaptation task. We first align the target and multiple source domains on domain-level by an adversarial learning process, and then reduce the domain gap on category-level by minimizing the distance between the category prototypes and target instances with a minimax entropy loss.
• We propose an instance weighting strategy to mitigate the impact of instance variations inside each domain.
• Experimental results on several datasets demonstrate the superiority of the proposed algorithm to several state-of-the-art approaches.
摘要
•We introduce a two-way alignment framework for unsupervised multisource domain adaptation task. We first align the target and multiple source domains on domain-level by an adversarial learning process, and then reduce the domain gap on category-level by minimizing the distance between the category prototypes and target instances with a minimax entropy loss.•We propose an instance weighting strategy to mitigate the impact of instance variations inside each domain.•Experimental results on several datasets demonstrate the superiority of the proposed algorithm to several state-of-the-art approaches.
论文关键词：Domain adaptation,Feature extraction,Category prototype,Adversarial training,Instance weighting
论文评审过程：Received 13 November 2020, Revised 30 June 2021, Accepted 9 November 2021, Available online 24 November 2021, Version of Record 4 December 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108430
