Graph Degree Linkage: Agglomerative Clustering on a Directed Graph

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.

Proceedings of European Conference on Computer Vision (ECCV), 2012

Cited by in corpus (8)

• Joint Unsupervised Learning of Deep Representations and Image Clusters
• Deep Continuous Clustering
• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
• The Impact of Isolation Kernel on Agglomerative Hierarchical Clustering Algorithms
• Factors in Finetuning Deep Model for object detection
• Merge or Not? Learning to Group Faces via Imitation Learning
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Saliency Detection via Combining Region-Level and Pixel-Level Predictions with CNNs