Maximum margin multiple-instance feature weighting
作者：
Highlights：
• We propose an algorithm utilized for multiple-instance feature weighting.
• The proposed algorithm adopts the maximum margin idea in the design work.
• It can be utilized for both binary-class and multi-class learning tasks.
• We utilize the coordinate ascent algorithm in the optimization work.
• We adopt synthetic and real-world datasets to test the effectiveness of our work.
摘要
•We propose an algorithm utilized for multiple-instance feature weighting.•The proposed algorithm adopts the maximum margin idea in the design work.•It can be utilized for both binary-class and multi-class learning tasks.•We utilize the coordinate ascent algorithm in the optimization work.•We adopt synthetic and real-world datasets to test the effectiveness of our work.
论文关键词：Feature weighting,Multiple-instance learning,Maximum margin,Coordinate ascent
论文评审过程：Received 9 March 2013, Revised 3 December 2013, Accepted 20 December 2013, Available online 3 January 2014.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.12.009
