Publication 2014 Issue No. 1 - Jan. Abstract - Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint
 This Article Share Bibliographic References Add to: Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb Search Similar Articles Articles by Ming-Yu Liu Articles by Oncel Tuzel Articles by Srikumar Ramalingam Articles by Rama Chellappa
Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint
Jan. 2014 (vol. 36 no. 1)
pp. 99-112
 ASCII Text x Ming-Yu Liu, Oncel Tuzel, Srikumar Ramalingam, Rama Chellappa, "Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 1, pp. 99-112, Jan., 2014.
 BibTex x @article{ 10.1109/TPAMI.2013.107,author = {Ming-Yu Liu and Oncel Tuzel and Srikumar Ramalingam and Rama Chellappa},title = {Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint},journal ={IEEE Transactions on Pattern Analysis and Machine Intelligence},volume = {36},number = {1},issn = {0162-8828},year = {2014},pages = {99-112},doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2013.107},publisher = {IEEE Computer Society},address = {Los Alamitos, CA, USA},}
 RefWorks Procite/RefMan/Endnote x TY - JOURJO - IEEE Transactions on Pattern Analysis and Machine IntelligenceTI - Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid ConstraintIS - 1SN - 0162-8828SP99EP112EPD - 99-112A1 - Ming-Yu Liu, A1 - Oncel Tuzel, A1 - Srikumar Ramalingam, A1 - Rama Chellappa, PY - 2014KW - discrete optimizationKW - ClusteringKW - superpixel segmentationKW - graph theoryKW - information theoryKW - submodular functionVL - 36JA - IEEE Transactions on Pattern Analysis and Machine IntelligenceER -
Ming-Yu Liu, Mitsubishi Electric Research Laboratories, Cambridge
Oncel Tuzel, Mitsubishi Electric Research Laboratories, Cambridge
Srikumar Ramalingam, Mitsubishi Electric Research Laboratories, Cambridge
Rama Chellappa, University of Maryland College Park, College Park
We propose a new objective function for clustering. This objective function consists of two components: the entropy rate of a random walk on a graph and a balancing term. The entropy rate favors formation of compact and homogeneous clusters, while the balancing function encourages clusters with similar sizes and penalizes larger clusters that aggressively group samples. We present a novel graph construction for the graph associated with the data and show that this construction induces a matroid--a combinatorial structure that generalizes the concept of linear independence in vector spaces. The clustering result is given by the graph topology that maximizes the objective function under the matroid constraint. By exploiting the submodular and monotonic properties of the objective function, we develop an efficient greedy algorithm. Furthermore, we prove an approximation bound of $({1\over 2})$ for the optimality of the greedy solution. We validate the proposed algorithm on various benchmarks and show its competitive performances with respect to popular clustering algorithms. We further apply it for the task of superpixel segmentation. Experiments on the Berkeley segmentation data set reveal its superior performances over the state-of-the-art superpixel segmentation algorithms in all the standard evaluation metrics.
Index Terms:
discrete optimization,Clustering,superpixel segmentation,graph theory,information theory,submodular function
Citation:
Ming-Yu Liu, Oncel Tuzel, Srikumar Ramalingam, Rama Chellappa, "Entropy-Rate Clustering: Cluster Analysis via Maximizing a Submodular Function Subject to a Matroid Constraint," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 1, pp. 99-112, Jan. 2014, doi:10.1109/TPAMI.2013.107