Graph Degree Linkage: Agglomerative Clustering on a Directed Graph

TL;DR

This paper introduces a graph-based agglomerative clustering algorithm that leverages indegree and outdegree concepts to improve robustness and efficiency in high-dimensional data clustering, with strong results in image clustering and object matching.

Contribution

It presents a novel affinity measure based on indegree and outdegree products, enhancing clustering robustness and efficiency, and demonstrates superior performance over existing methods.

Findings

Outperforms state-of-the-art methods in image clustering

Achieves better accuracy in object matching tasks

Offers a simple and computationally efficient algorithm

Abstract

This paper proposes a simple but effective graph-based agglomerative algorithm, for clustering high-dimensional data. We explore the different roles of two fundamental concepts in graph theory, indegree and outdegree, in the context of clustering. The average indegree reflects the density near a sample, and the average outdegree characterizes the local geometry around a sample. Based on such insights, we define the affinity measure of clusters via the product of average indegree and average outdegree. The product-based affinity makes our algorithm robust to noise. The algorithm has three main advantages: good performance, easy implementation, and high computational efficiency. We test the algorithm on two fundamental computer vision problems: image clustering and object matching. Extensive experiments demonstrate that it outperforms the state-of-the-arts in both applications.