Ensemble Quadratic Assignment Network for Graph Matching

arXiv:2403.06457v1 Announce Type: new
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 …

abstract accuracy algorithm arxiv computer computer vision cs.cv data data-driven ensemble feature global graph network nodes outlier paper pattern recognition recognition robust rotation transformation type vision