Robust multi-source adaptation visual classification using supervised low-rank representation

作者：

Highlights：

• Present a Robust Multi-source Adaptation framework using supervised low rank representation.

• Jointly optimize the supervised low rank representation and the adaptive classification model.

• We further propose two effective extensions.

• A generalization error bound is also derived for our extension.

• Comprehensive experiments verify the robustness and effectiveness of our methods.

摘要

•Present a Robust Multi-source Adaptation framework using supervised low rank representation.•Jointly optimize the supervised low rank representation and the adaptive classification model.•We further propose two effective extensions.•A generalization error bound is also derived for our extension.•Comprehensive experiments verify the robustness and effectiveness of our methods.

论文关键词：Multiple source domain adaptation,Transfer learning,Supervised low rank representation,Visual classification

论文评审过程：Received 16 September 2014, Revised 19 May 2016, Accepted 3 July 2016, Available online 5 July 2016, Version of Record 2 August 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.07.006