Share Email Print
cover

Proceedings Paper

Feature pooling for small visual dictionaries
Author(s): Xianglin Huang; Ye Xu; Lifang Yang; Jianglong Zhang
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Large visual dictionaries are often used to achieve good image classification performance in bag-of-features (BoF) model, while they lead to high computational cost on dictionary learning and feature coding. In contrast, using small dictionaries can largely reduce the computational cost but result in poor classification performance. Some works have pointed out that pooling locally across feature space can boost the classification performance especially for small dictionaries. Following this idea, various pooling strategies have been proposed in recent years, but they are not good enough for small dictionaries. In this paper, we present a unified framework of pooling operation, and propose two novel pooling strategies to improve the performance of small dictionaries with low extra computational cost. Experimental results on two challenging image classification benchmarks show that our pooling strategies outperform others in most cases.

Paper Details

Date Published: 29 August 2016
PDF: 7 pages
Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100335U (29 August 2016); doi: 10.1117/12.2243998
Show Author Affiliations
Xianglin Huang, Communication Univ. of China (China)
Ye Xu, Communication Univ. of China (China)
Lifang Yang, Communication Univ. of China (China)
Jianglong Zhang, Communication Univ. of China (China)


Published in SPIE Proceedings Vol. 10033:
Eighth International Conference on Digital Image Processing (ICDIP 2016)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top