Feedback mechanism based iterative metric learning for person re-identification

作者：

Highlights：

• A feedback mechanism back propagates identification results to join into metric learning.

• Distances of multiple metric projections are combined to deal with the over fitting problem.

• A novel method learns distance metric in an iterative way.

摘要

•A feedback mechanism back propagates identification results to join into metric learning.•Distances of multiple metric projections are combined to deal with the over fitting problem.•A novel method learns distance metric in an iterative way.

论文关键词：Person re-identification,Metric learning,Feedback,Iteration

论文评审过程：Received 15 November 2016, Revised 6 April 2017, Accepted 12 April 2017, Available online 18 April 2017, Version of Record 21 November 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.04.012