Combining local and global: Rich and robust feature pooling for visual recognition

作者：

Highlights：

• A novel pooling method is proposed to extract features in an unsupervised framework.

• The proposed method learns features from both the global and the local feature space.

• Multiple resolutions of features are learnt.

• The proposed method is insensitive to the parameters and the input data.

摘要

Highlights•A novel pooling method is proposed to extract features in an unsupervised framework.•The proposed method learns features from both the global and the local feature space.•Multiple resolutions of features are learnt.•The proposed method is insensitive to the parameters and the input data.

论文关键词：Unsupervised learning,Spatial pooling,Auto-encoder

论文评审过程：Received 4 March 2016, Revised 30 May 2016, Accepted 9 August 2016, Available online 17 August 2016, Version of Record 30 September 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.08.006