OPML: A one-pass closed-form solution for online metric learning

作者：

Highlights：

• A one-pass triplet construction strategy with very low space and time complexity.

• A closed-form solution to update the metric with very low time complexity.

• An extension to solve cold start issue.

• Flexible way to employ hand-crafted or deeply-learned features.

• Theoretical analyses to guarantee the effectiveness of our methods.

摘要

•A one-pass triplet construction strategy with very low space and time complexity.•A closed-form solution to update the metric with very low time complexity.•An extension to solve cold start issue.•Flexible way to employ hand-crafted or deeply-learned features.•Theoretical analyses to guarantee the effectiveness of our methods.

论文关键词：One-pass,Online metric learning,Triplet construction,Face verification,Abnormal event detection

论文评审过程：Received 28 September 2016, Revised 12 January 2017, Accepted 8 March 2017, Available online 9 March 2017, Version of Record 21 November 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.03.016