A Joint Optimization Framework of Sparse Coding and Discriminative Clustering
A Joint Optimization Framework of Sparse Coding and Discriminative Clustering
复制标题
DOI：
--
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Zhangyang Wang;Yingzhen Yang;Shiyu Chang;Jinyan Li;S. Fong;Thomas S. Huang
中科院分区：
文献类型：
--
作者：
Zhangyang Wang;Yingzhen Yang;Shiyu Chang;Jinyan Li;S. Fong;Thomas S. Huang
许多聚类方法高度依赖于提取的特征。本文从特征提取和判别聚类两个方面提出了一种联合优化框架。我们利用图正则稀疏编码作为特征，并将稀疏编码作为聚类的约束条件。分别基于最小熵和最大间隔聚类原则建立了两个代价函数，作为最小化的目标。求解这样的双层优化相互加强了稀疏编码和集群步骤。在多个基准数据集上的实验验证了所提出的联合优化所带来的显著性能改善。
Many clustering methods highly depend on extracted features. In this paper, we propose a joint optimization framework in terms of both feature extraction and discriminative clustering. We utilize graph regularized sparse codes as the features, and formulate sparse coding as the constraint for clustering. Two cost functions are developed based on entropy-minimization and maximum-margin clustering principles, respectively, as the objectives to be minimized. Solving such a bi-level optimization mutually reinforces both sparse coding and clustering steps. Experiments on several benchmark datasets verify remarkable performance improvements led by the proposed joint optimization.