Fast Clustering With Co-Clustering Via Discrete Non-Negative Matrix Factorization for Image Identification

Abstract

How to effectively cluster large-scale image data sets is a challenge and is receiving more and more attention. To address this problem, a novel clustering method called fast clustering with co-clustering via discrete non-negative matrix factorization, is proposed. Inspired by co-clustering, our algorithm reduces computational complexity by transforming clustering tasks into co-clustering tasks. Although our model has the same form of objective function as normalized cut, we relax it to a matrix decomposition problem, which is different from most graph-based approaches. In addition, an efficient optimization algorithm is proposed to solve the relaxed problem, where a discrete solution corresponding to the clustering result can be directly obtained. Extensive experiments have been conducted on several synthetic data sets and real word data sets. Compared with the state-of-the-art clustering methods, the proposed algorithm achieves very promising performance.