A Graph-Matching Kernel for Object Categorization
Abstract
This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.
Cite
Text
Duchenne et al. "A Graph-Matching Kernel for Object Categorization." IEEE/CVF International Conference on Computer Vision, 2011. doi:10.1109/ICCV.2011.6126445Markdown
[Duchenne et al. "A Graph-Matching Kernel for Object Categorization." IEEE/CVF International Conference on Computer Vision, 2011.](https://mlanthology.org/iccv/2011/duchenne2011iccv-graph/) doi:10.1109/ICCV.2011.6126445BibTeX
@inproceedings{duchenne2011iccv-graph,
title = {{A Graph-Matching Kernel for Object Categorization}},
author = {Duchenne, Olivier and Joulin, Armand and Ponce, Jean},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2011},
pages = {1792-1799},
doi = {10.1109/ICCV.2011.6126445},
url = {https://mlanthology.org/iccv/2011/duchenne2011iccv-graph/}
}