Carnegie Mellon University
Unsupervised Learning for Graph Matching

Marius Leordeanu and Martial Hebert
Computer Vision and Pattern Recognition (CVPR '09), June, 2009.

  • Adobe portable document format (pdf) (4MB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Graph matching is an important problem in computer vision. It is used in 2D and 3D object matching and recognition. Despite its importance, there is little literature on learning the parameters that control the graph matching problem, even though learning is important for improving the matching rate, as shown by this and other work. In this paper we show for the first time how to perform parameter learning in an unsupervised fashion, that is when no correct correspondences between graphs are given during training. We show empirically that unsupervised learning is comparable in efficiency and quality with the supervised one, while avoiding the tedious manual labeling of ground truth correspondences. We also verify experimentally that this learning method can improve the performance of several state-of-the art graph matching algorithms.

computer vision, graph matching, learning for graph matching

Number of pages: 8
Note: (to appear)

Text Reference
Marius Leordeanu and Martial Hebert , "Unsupervised Learning for Graph Matching," Computer Vision and Pattern Recognition (CVPR '09), June, 2009.

BibTeX Reference
   author = "Marius Leordeanu and Martial {Hebert }",
   title = "Unsupervised Learning for Graph Matching",
   booktitle = "Computer Vision and Pattern Recognition (CVPR '09)",
   month = "June",
   year = "2009",
   Notes = "(to appear)"