R2FP: Rich and robust feature pooling for mining visual data
Publication Type
Conference Proceeding Article
Publication Date
11-2015
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 a novel pooling method within an unsupervised feature learning framework, named Rich and Robust Feature Pooling (R2FP), to better explore rich and robust representation from sparse feature maps of the input data. Both local and global pooling strategies are further considered to instantiate such a method and intensively studied. The former selects the most conductive features in the sub-region and summarizes the joint distribution of the selected features, while the latter is utilized to extract multiple resolutions of features and fuse the features with a feature balancing kernel for rich representation. Extensive experiments on several image recognition tasks demonstrate the superiority of the proposed techniques.
Keywords
Autoencoder, Pooling, Representation learning
Discipline
Computer Sciences | Databases and Information Systems
Publication
ICDM 2015: Proceedings of the 15th IEEE International Conference on Data Mining: Atlantic City, NJ, November 14-17, 2015
First Page
469
Last Page
478
ISBN
9781467395038
Identifier
10.1109/ICDM.2015.98
Publisher
IEEE
City or Country
Piscataway, NJ
Citation
XIONG, Wei; DU, Bo; ZHANG, Lefei; HU, Ruimin; BIAN, Wei; SHEN, Jialie; and TAO, Dacheng.
R2FP: Rich and robust feature pooling for mining visual data. (2015). ICDM 2015: Proceedings of the 15th IEEE International Conference on Data Mining: Atlantic City, NJ, November 14-17, 2015. 469-478.
Available at: https://ink.library.smu.edu.sg/sis_research/3539
Additional URL
http://doi.org/10.1109/ICDM.2015.98