mlsanityData to 14 Oct 2026

Fusion Moves for Graph Matching

arXiv 2101.12085 ↗First posted 28 Jan 2021cs.CV math.OCcited by 16

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 14 of its 59 references that are in the map. First posted on arXiv 28 Jan 2021.

Builds on

14 of 59 references.

References · 14

  1. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  2. 2019Learning Combinatorial Embedding Networks for Deep Graph Matchingcited by 99
  3. 2020Deep Graph Matching Consensuscited by 85
  4. 2019Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matchingcited by 84
  5. 2020Deep Graph Matching via Blackbox Differentiation of Combinatorial Solverscited by 81
  6. 2016A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matchingcited by 26
  7. 2017DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problemscited by 20
  8. 2014A Comparative Study of Modern Inference Techniques for Structured Discrete Energy Minimization Problemscited by 16
  9. 2020MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Modelscited by 10
  10. 2019GLMNet: Graph Learning-Matching Networks for Feature Matchingcited by 9
  11. 2020Discrete graphical models -- an optimization perspectivecited by 8
  12. 2020Taxonomy of Dual Block-Coordinate Ascent Methods for Discrete Energy Minimizationcited by 8
2 more
  1. 2016A Dual Ascent Framework for Lagrangean Decomposition of Combinatorial Problemscited by 7
  2. 2020Exact MAP-Inference by Confining Combinatorial Search with LP Relaxationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 3; 2024: 2; 2025: 5; 2026: 1.

16 papers.

Sort:

  1. 2022A Comparative Study of Graph Matching Algorithms in Computer Visioncited by 14
  2. 2025It's a (Blind) Match! Towards Vision-Language Correspondence without Parallel Datacited by 14
  3. 2023CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapescited by 11
  4. 2021FastDOG: Fast Discrete Optimization on GPUcited by 8
  5. 2022DOGE-Train: Discrete Optimization on GPU with End-to-end Trainingcited by 6
  6. 2025Quantum-enhanced Computer Vision: Going Beyond Classical Algorithmscited by 5
  7. 2022Structured Prediction Problem Archivecited by 4
  8. 2022Review of Serial and Parallel Min-Cut/Max-Flow Algorithms for Computer Visioncited by 2
  9. 2023Unsupervised Deep Graph Matching Based on Cycle Consistencycited by 2
  10. 2024Optimizing Incomplete, Large-Scale and Sparse Multi-Graph Matching in Bioimagingcited by 2
  11. 2023Relative-Interior Solution for the (Incomplete) Linear Assignment Problem with Applications to the Quadratic Assignment Problemcited by 1
  12. 2025Normalized Matching Transformercited by 1
4 more
  1. 2024Correlation Clustering of Organoid Imagescited by 0
  2. 2025Cycle-Consistent Multi-Graph Matching for Self-Supervised Annotation of C.Eleganscited by 0
  3. 2025Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communicationcited by 0
  4. 2026Fast and Compact Graph Cuts for the Boykov-Kolmogorov Algorithmcited by 0