Filter-in-Filter: Low Cost CNN Improvement by Sub-filter Parameter Sharing

作者：

Highlights：

• We defined the sub-filters of a filter and visualized them to verify these sub-filters can recognize multiple meaningful patterns.

• Filter-in-Filter was proposed to make full use of the sub-filters to enhance the expressibility of the filters in CNNs.

• Filter-in-Filter does not increase the number of parameters and increases the computational cost only slightly as compared to the standard convolution. We verified that FIF is effective to improve the performance of CNNs by conducting extensive experiments.

摘要

•We defined the sub-filters of a filter and visualized them to verify these sub-filters can recognize multiple meaningful patterns.•Filter-in-Filter was proposed to make full use of the sub-filters to enhance the expressibility of the filters in CNNs.•Filter-in-Filter does not increase the number of parameters and increases the computational cost only slightly as compared to the standard convolution. We verified that FIF is effective to improve the performance of CNNs by conducting extensive experiments.

论文关键词：Sub-pattern,Sub-filter,Expressibility of filter,Visualization,Filter-in-filter

论文评审过程：Received 31 July 2018, Revised 20 January 2019, Accepted 30 January 2019, Available online 7 February 2019, Version of Record 27 March 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.01.044