Object proposal with kernelized partial ranking
作者：
Highlights：
• In this paper, we propose a new partial ranking algorithm with support of non- linear kernel.
• We perform consistent weighted sampling on the features followed by learning our partial ranking model. Here learning a ranking model with non-linear kernel amounts to learning a linear hyperplane.
• Our algorithm greatly promotes baseline proposal generation methods in recall and average recall.
• Our method can be integrated with any proposal generation methods.
摘要
•In this paper, we propose a new partial ranking algorithm with support of non- linear kernel.•We perform consistent weighted sampling on the features followed by learning our partial ranking model. Here learning a ranking model with non-linear kernel amounts to learning a linear hyperplane.•Our algorithm greatly promotes baseline proposal generation methods in recall and average recall.•Our method can be integrated with any proposal generation methods.
论文关键词：Object proposal,Partial ranking,Consistent weighted sampling
论文评审过程：Received 14 August 2016, Revised 29 January 2017, Accepted 19 March 2017, Available online 25 April 2017, Version of Record 4 May 2017.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.03.022
