Learning Hypergraph Labeling for Feature Matching

TL;DR

This paper introduces a hypergraph labeling approach for feature matching, modeling candidate matches and their subsets as hypergraph nodes and hyperedges, and learns the cost function to improve matching accuracy.

Contribution

It proposes a novel hypergraph-based feature matching method that learns the labeling cost function from data, enhancing performance over existing higher-order methods.

Findings

Learning improves matching accuracy on standard datasets.

Hypergraph approach outperforms non-learning higher-order methods.

Method effectively models subset interactions for better correspondence.

Abstract

This study poses the feature correspondence problem as a hypergraph node labeling problem. Candidate feature matches and their subsets (usually of size larger than two) are considered to be the nodes and hyperedges of a hypergraph. A hypergraph labeling algorithm, which models the subset-wise interaction by an undirected graphical model, is applied to label the nodes (feature correspondences) as correct or incorrect. We describe a method to learn the cost function of this labeling algorithm from labeled examples using a graphical model training algorithm. The proposed feature matching algorithm is different from the most of the existing learning point matching methods in terms of the form of the objective function, the cost function to be learned and the optimization method applied to minimize it. The results on standard datasets demonstrate how learning over a hypergraph improves the matching performance over existing algorithms, notably one that also uses higher order information without learning.