Multi-View Analysis Dictionary Learning for Image Classification

A great number of studies show that considering information from multiple views results in better performance than their single-view counterparts. However, many previous works aiming to improve classification performance fail to effectively tackle the inter-view correlation or the intra-class variability. Analysis dictionary learning (ADL) has theoretic significance and practical potential in classification tasks. Based on the ADL, this paper proposes a new method, namely, multi-view analysis dictionary learning (MvADL) for image classification. Specifically, multi-view analysis dictionaries are designed to reduce the intra-class variability in the transformed space in the multi-view scenario. Then, a marginalized classification term is incorporated to integrate the semantic information into the basic dictionary learning model. In the marginalized classification term, a marginalized target learning strategy is applied to improve the flexibility and discriminability of the whole model. Besides, an iteratively optimizing algorithm is designed to solve the proposed MvADL. Experiments on benchmark data sets demonstrate the superiority of our proposed method.