Deep conditional adaptation networks and label correlation transfer for unsupervised domain adaptation

作者：

Highlights：

• Presenting a conditional adaptation networks for cross-domain image classification.

• Solving the categories mismatch and class prior bias problems by conditional adaptation.

• Proposing a label correlation transfer algorithm to preserve the domain information.

• Experiments are performed to show the usefulness of the proposed method.

摘要

•Presenting a conditional adaptation networks for cross-domain image classification.•Solving the categories mismatch and class prior bias problems by conditional adaptation.•Proposing a label correlation transfer algorithm to preserve the domain information.•Experiments are performed to show the usefulness of the proposed method.

论文关键词：Conditional domain adaptation,Deep learning,Unsupervised learning,Label transfer

论文评审过程：Received 29 November 2018, Revised 21 July 2019, Accepted 27 September 2019, Available online 28 September 2019, Version of Record 8 October 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107072