Adaptive spatial pooling for image classification
作者：
Highlights：
• Pooling operator is parameterized as a distribution matrix.
• Each category enjoys its own pooling operator.
• The pooling distribution learning and the classifier training are jointly formulated.
• The problem is solved efficiently via a boosting-like algorithm.
• The proposed models outperform many other popular methods.
摘要
Highlights•Pooling operator is parameterized as a distribution matrix.•Each category enjoys its own pooling operator.•The pooling distribution learning and the classifier training are jointly formulated.•The problem is solved efficiently via a boosting-like algorithm.•The proposed models outperform many other popular methods.
论文关键词：Weighted pooling,Spatial layout,Distribution matrix,Image classification
论文评审过程：Received 11 February 2015, Revised 15 October 2015, Accepted 27 January 2016, Available online 11 February 2016, Version of Record 21 March 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2016.01.030
