A comparative study of graph matching algorithms in computer vision

Item Type:	Article
Title:	A comparative study of graph matching algorithms in computer vision
Creators Name:	Haller, S. and Feineis, L. and Hutschenreiter, L. and Bernard, F. and Rother, C. and Kainmüller, D. and Swoboda, P. and Savchynskyy, B.
Abstract:	The graph matching optimization problem is an essential component for many tasks in computer vision, such as bringing two deformable objects in correspondence. Naturally, a wide range of applicable algorithms have been proposed in the last decades. Since a common standard benchmark has not been developed, their performance claims are often hard to verify as evaluation on differing problem instances and criteria make the results incomparable. To address these shortcomings, we present a comparative study of graph matching algorithms. We create a uniform benchmark where we collect and categorize a large set of existing and publicly available computer vision graph matching problems in a common format. At the same time we collect and categorize the most popular open-source implementations of graph matching algorithms. Their performance is evaluated in a way that is in line with the best practices for comparing optimization algorithms. The study is designed to be reproducible and extensible to serve as a valuable resource in the future. Our study provides three notable insights: 1.) popular problem instances are exactly solvable in substantially less than 1 second and, therefore, are insufficient for future empirical evaluations; 2.) the most popular baseline methods are highly inferior to the best available methods; 3.) despite the NP-hardness of the problem, instances coming from vision applications are often solvable in a few seconds even for graphs with more than 500 vertices.
Keywords:	Graph Matching, Optimization, Benchmark
Source:	Lecture Notes in Computer Science
Title of Book:	Computer Vision - ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXIII
ISSN:	0302-9743
ISBN:	978-3-031-20049-6
Publisher:	Springer
Volume:	13683
Page Range:	636-653
Date:	2022
Official Publication:	https://doi.org/10.48550/arXiv.2207.00291

Repository Staff Only: item control page