Learning Graphs to Match
Abstract
Many tasks in computer vision are formulated as graph matching problems. Despite the NP-hard nature of the problem, fast and accurate approximations have led to significant progress in a wide range of applications. Learning graph models from observed data, however, still remains a challenging issue. This paper presents an effective scheme to parameterize a graph model, and learn its structural attributes for visual object matching. For this, we propose a graph representation with histogram-based attributes, and optimize them to increase the matching accuracy. Experimental evaluations on synthetic and real image datasets demonstrate the effectiveness of our approach, and show significant improvement in matching accuracy over graphs with pre-defined structures.
Cite
Text
Cho et al. "Learning Graphs to Match." International Conference on Computer Vision, 2013. doi:10.1109/ICCV.2013.11Markdown
[Cho et al. "Learning Graphs to Match." International Conference on Computer Vision, 2013.](https://mlanthology.org/iccv/2013/cho2013iccv-learning/) doi:10.1109/ICCV.2013.11BibTeX
@inproceedings{cho2013iccv-learning,
title = {{Learning Graphs to Match}},
author = {Cho, Minsu and Alahari, Karteek and Ponce, Jean},
booktitle = {International Conference on Computer Vision},
year = {2013},
doi = {10.1109/ICCV.2013.11},
url = {https://mlanthology.org/iccv/2013/cho2013iccv-learning/}
}