Class-Specific Sparse Principal Component Analysis for Visual Classification

Extensive research has demonstrated that dictionary learning is active in improving the performance of the representation based classification. However, dictionary learning suffers from lacking an effective dictionary structure that can well tradeoff the reducing reconstruction error and enhancing the representative information. In this paper, we focus on designing capable dictionary learning architecture for the visual classification task with few-shot training samples. First, we propose a class-specific sparse PCA approach to extend the conventional dictionary learning to dictionary pair learning for visual classification. The orthogonal synthesis dictionary ensures fewer reconstruction errors with fixed dictionary size while the sparse analysis dictionary guarantees the representative features. Second, we develop the Alternating Direction Method of Multipliers algorithm to optimize the analysis dictionary to improve computational efficiency. Extensive experiments conducted on multiple image datasets demonstrate that the proposed class-specific PCA method performs favorably against the state-of-art methods on eight widely used image datasets.