Paper
29 August 2016 Feature pooling for small visual dictionaries
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100335U (2016) https://doi.org/10.1117/12.2243998
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
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.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xianglin Huang, Ye Xu, Lifang Yang, and Jianglong Zhang "Feature pooling for small visual dictionaries", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100335U (29 August 2016); https://doi.org/10.1117/12.2243998
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Visualization

Associative arrays

Principal component analysis

Image classification

Performance modeling

Image compression

Computer programming

Back to Top