Fusion Moves for Graph Matching

Lisa Hutschenreiter, Stefan Haller, Lorenz Feineis, Carsten Rother, Dagmar Kainm├╝ller, Bogdan Savchynskyy; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 6270-6279

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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Hutschenreiter_2021_ICCV, author = {Hutschenreiter, Lisa and Haller, Stefan and Feineis, Lorenz and Rother, Carsten and Kainm\"uller, Dagmar and Savchynskyy, Bogdan}, title = {Fusion Moves for Graph Matching}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {6270-6279} }