PSSDL: Probabilistic Semi-supervised Dictionary Learning
Behnam Babagholami-Mohamadabadi, Ali Zarghami, Mohammadreza Zolfaghari, Baghshah Mahdieh Soleymani · 2013
Abstract. While recent supervised dictionary learning methods have attained promising results on the classication tasks, their performance depends on the availability of the large labeled datasets. However, in many real world applications, accessing to sucient labeled data may be expensive and/or time consuming, but its relatively easy to acquire a large amount of unlabeled data. In this paper, we propose a probabilistic framework for discriminative dictionary learning which uses both the labeled and unlabeled data. Experimental results demonstrate that the performance of the proposed method is signicantly better than the state of the art dictionary based classication methods.