Fusion moves for graph matching

Tools

Item Type:	Conference or Workshop Item
Title:	Fusion moves for graph matching
Creators Name:	Hutschenreiter, L., Haller, S., Feineis, L., Rother, C., Kainmüller, D. and Savchynskyy, B.
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 bioimaging 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.
Keywords:	Optimization and Learning Methods, Computer Vision, Approximation Algorithms, Markov Random Fields
Source:	2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Series Name:	IEEE/CVF International Conference on Computer Vision (ICCV)
Title of Book:	2021 IEEE/CVF International Conference on Computer Vision (ICCV)
ISSN:	2380-7504
ISBN:	978-1-6654-2812-5
Publisher:	IEEE
Page Range:	6250-6259
Date:	28 February 2022
Additional Information:	Copyright © 2021 IEEE
Official Publication:	https://doi.org/10.1109/ICCV48922.2021.00621
External Fulltext:	View full text on external repository or document server

Repository Staff Only: item control page