Visual domain adaptation based on modified A−distance and sparse filtering
作者：
Highlights：
• A novel model is proposed for domain adaptation, which does not require any labels from source or target domain during training.
• We modify A-distance by solving the linear classification problem with pseudo inverse.
• We use the learning paradigm of sparse filtering to preserve the structure of data, and point out that within-domain normalization is more suitable for domain adaptation problems.
摘要
•A novel model is proposed for domain adaptation, which does not require any labels from source or target domain during training.•We modify A-distance by solving the linear classification problem with pseudo inverse.•We use the learning paradigm of sparse filtering to preserve the structure of data, and point out that within-domain normalization is more suitable for domain adaptation problems.
论文关键词：Domain adaptation,A−distance,Sparse filtering
论文评审过程：Received 21 April 2019, Revised 1 November 2019, Accepted 30 January 2020, Available online 31 January 2020, Version of Record 16 March 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107254
