Fusion Moves for Graph Matching
From MaRDI portal
Publication:6359290
arXiv2101.12085MaRDI QIDQ6359290
Author name not available (Why is that?)
Publication date: 28 January 2021
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.
Has companion code repository: https://github.com/vislearn/libmpopt
This page was built for publication: Fusion Moves for Graph Matching
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6359290)
