Multiple Spatial Pooling for Visual Object Recognition
 |
| The unified framework of multiple pooling |
People
Yongzhen Huang
Zifeng Wu
Liang Wang
Chunfeng Song
Overview
Global spatial structure is an important factor for visual object recognition but has not attracted sufficient attention in recent studies. Especially, the problems of features' ambiguity and sensitivity to location change in the image space are not yet well solved. In this paper, we propose multiple spatial pooling (MSP) to address these problems. MSP models global spatial structure with multiple Gaussian distributions and then pools features according to there lations between features and Gaussian distributions. Such a process is further generalized into a unified framework, which formulates multiple pooling using matrix operation with structured sparsity. Experiments in terms of scene classification and object categorization demonstrate that MSP can enhance traditional algorithms with small extra computational cost.
Paper
 |
Multiple Spatial Pooling for Visual Object Recognition Yongzhen Huang, Zifeng Wu, Liang Wang, Chunfeng Song Neurocomputing (NEUCOM2014) |
Experimental Results
 |
|
| Comparison between SPM and MSP in different levels | Comparison of three algorithms under different testing conditions |
Acknowledgments
This work is jointly supported by the National Natural Science Foundation of China(61175003,61135002,61203252),Hundred Talents Program of CAS, and Tsinghua National Laboratory for Information Science and Technology Cross-discipline Foundation.