R2FP: Rich and Robust Feature Pooling for Mining Visual Data

Abstract

The human visual system proves smart in extracting both global and local features. Can we design a similar way for unsupervised feature learning? In this paper, we propose anovel pooling method within an unsupervised feature learningframework, named Rich and Robust Feature Pooling (R2FP), to better explore rich and robust representation from sparsefeature maps of the input data. Both local and global poolingstrategies are further considered to instantiate such a methodand intensively studied. The former selects the most conductivefeatures in the sub-region and summarizes the joint distributionof the selected features, while the latter is utilized to extractmultiple resolutions of features and fuse the features witha feature balancing kernel for rich representation. Extensiveexperiments on several image recognition tasks demonstratethe superiority of the proposed techniques.

DOI: 10.1109/ICDM.2015.98

9 Figures and Tables

Cite this paper

@article{Xiong2015R2FPRA, title={R2FP: Rich and Robust Feature Pooling for Mining Visual Data}, author={Wei Xiong and Bo Du and Lefei Zhang and Ruimin Hu and Wei Bian and Jialie Shen and Dacheng Tao}, journal={2015 IEEE International Conference on Data Mining}, year={2015}, pages={469-478} }