English

Ensemble Quadratic Assignment Network for Graph Matching

Computer Vision and Pattern Recognition 2024-03-12 v1

Abstract

Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably, whereas some traditional algorithm-based methods are more robust to feature noises, outlier nodes, and global transformation (e.g.~rotation). In this paper, we propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods. In the GNN framework, we transform traditional graph-matching solvers as single-channel GNNs on the association graph and extend the single-channel architecture to the multi-channel network. The proposed model can be seen as an ensemble method that fuses multiple algorithms at every iteration. Instead of averaging the estimates at the end of the ensemble, in our approach, the independent iterations of the ensembled algorithms exchange their information after each iteration via a 1x1 channel-wise convolution layer. Experiments show that our model improves the performance of traditional algorithms significantly. In addition, we propose a random sampling strategy to reduce the computational complexity and GPU memory usage, so the model applies to matching graphs with thousands of nodes. We evaluate the performance of our method on three tasks: geometric graph matching, semantic feature matching, and few-shot 3D shape classification. The proposed model performs comparably or outperforms the best existing GNN-based methods.

Keywords

Cite

@article{arxiv.2403.06457,
  title  = {Ensemble Quadratic Assignment Network for Graph Matching},
  author = {Haoru Tan and Chuang Wang and Sitong Wu and Xu-Yao Zhang and Fei Yin and Cheng-Lin Liu},
  journal= {arXiv preprint arXiv:2403.06457},
  year   = {2024}
}

Comments

Accepted by IJCV in 2024

R2 v1 2026-06-28T15:15:21.894Z