Discriminative Paired Dictionary Learning for Visual Recognition
Hui-Hung Wang, Yi‐Ling Chen, Chen-Kuo Chiang · 2016
A Paired Discriminative K-SVD (PD-KSVD) dictionary learning method is presented in this paper for visual recognition. To achieve high discrimination and low reconstruction errors simultaneously for sparse coding, we propose to learn class-specific sub-dictionaries from pairs of positive and negative classes to jointly reduce the reconstruction errors of positive classes while keeping the reconstruction errors of negative classes high. Then, multiple sub-dictionaries are concatenated with respect to the same negative class so that the non-zero sparse coefficients can be discriminatively distributed to improve classification accuracy. Compared to the current dictionary learning methods, the proposed PD-KSVD method achieves very competitive performance in a variety of visual recognition tasks on several publicly available datasets.