Please use this identifier to cite or link to this item:
Title: Geometric ℓp-norm feature pooling for image classification
Authors: Feng, J.
Ni, B.
Tian, Q.
Yan, S. 
Issue Date: 2011
Citation: Feng, J.,Ni, B.,Tian, Q.,Yan, S. (2011). Geometric ℓp-norm feature pooling for image classification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 2697-2704. ScholarBank@NUS Repository.
Abstract: Modern visual classification models generally include a feature pooling step, which aggregates local features over the region of interest into a statistic through a certain spatial pooling operation. Two commonly used operations are the average and max poolings. However, recent theoretical analysis has indicated that neither of these two pooling techniques may be qualified to be optimal. Besides, we further reveal in this work that more severe limitations of these two pooling methods are from the unrecoverable loss of the spatial information during the statistical summarization and the underlying over-simplified assumption about the feature distribution. We aim to address these inherent issues in this work and generalize previous pooling methods as follows. We define a weighted ℓp-norm spatial pooling function tailored for the class-specific feature spatial distribution. Moreover, a sensible prior for the feature spatial correlation is incorporated. Optimizing such pooling function towards optimal class separability yields a so-called geometric ℓp-norm pooling (GLP) method. The described GLP method is capable of preserving the class-specific spatial/geometric information in the pooled features and significantly boosts the discriminating capability of the resultant features for image classification. Comprehensive evaluations on several image benchmarks demonstrate that the proposed GLP method can boost the image classification performance with a single type of feature to outperform or be comparable with the state-of-the-arts. © 2011 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISBN: 9781457703942
ISSN: 10636919
DOI: 10.1109/CVPR.2011.5995370
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Oct 11, 2019

Page view(s)

checked on Oct 12, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.