TL;DR
This paper introduces an enhanced graph matching algorithm using fusion moves, significantly improving solution quality and speed over existing methods, and setting a new state-of-the-art benchmark.
Contribution
It adapts fusion moves to graph matching, combining it with dual methods to achieve superior performance in speed and accuracy.
Findings
Fusion moves improve graph matching solutions.
The method outperforms existing algorithms in speed and quality.
Achieves a new state-of-the-art in graph matching benchmarks.
Abstract
We contribute to approximate algorithms for the quadratic assignment problem also known as graph matching. Inspired by the success of the fusion moves technique developed for multilabel discrete Markov random fields, we investigate its applicability to graph matching. In particular, we show how fusion moves can be efficiently combined with the dedicated state-of-the-art dual methods that have recently shown superior results in computer vision and bio-imaging applications. As our empirical evaluation on a wide variety of graph matching datasets suggests, fusion moves significantly improve performance of these methods in terms of speed and quality of the obtained solutions. Our method sets a new state-of-the-art with a notable margin with respect to its competitors.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
