Non-negative matrix fa^torization （NMF） is a useful technique to learn a parts-based representation by decom- posing the original data matrix into a basis set and coefficients with non-negative constraints. However,...Non-negative matrix fa^torization （NMF） is a useful technique to learn a parts-based representation by decom- posing the original data matrix into a basis set and coefficients with non-negative constraints. However, as an unsupervised method, the original NMF cannot utilize the discriminative class information. In this paper, we propose a semi-supervised class-driven NMF method to associate a class label with each basis vector by introducing an inhomogeneous representation cost constraint. This constraint forces the learned basis vectors to represent better for their own classes but worse for the others. Therefore, data samples in the same class will have similar representations, and consequently the discriminability in new representations could be boosted. Some experiments carried out on several standard databases validate the effectiveness of our method in comparison with the state-of-the-art approaches.展开更多
基金supported in part by the National Basic Research 973 Program of China under Grant No. 2012CB316400the National Natural Science Foundation of China under Grant Nos. 61025013, 61172129, 61210006+1 种基金the Fundamental Research Funds for the Central Universities of China under Grant No. 2012JBZ012the Program for Changjiang Scholars and Innovative Research Team in University of China under Grant No. IRT201206
文摘Non-negative matrix fa^torization （NMF） is a useful technique to learn a parts-based representation by decom- posing the original data matrix into a basis set and coefficients with non-negative constraints. However, as an unsupervised method, the original NMF cannot utilize the discriminative class information. In this paper, we propose a semi-supervised class-driven NMF method to associate a class label with each basis vector by introducing an inhomogeneous representation cost constraint. This constraint forces the learned basis vectors to represent better for their own classes but worse for the others. Therefore, data samples in the same class will have similar representations, and consequently the discriminability in new representations could be boosted. Some experiments carried out on several standard databases validate the effectiveness of our method in comparison with the state-of-the-art approaches.
