Object co-detection via low-rank and sparse representation dictionary learning

In this paper, we exploit an algorithm for detecting the individual objects from multiple images in a weakly supervised manner. Specifically, we treat the object co-detection as a jointly dictionary learning and objects localization problem. Thus a novel low-rank and sparse representation dictionary learning algorithm is proposed. It aims to learn a compact and discriminative dictionary associated with the specific object category. Different from previous dictionary learning methods, the sparsity imposed on representation coefficients, the rank minimization of learned dictionary, data reconstruction error and the low-rank constraint of sample data are all incorporated in a unitized objective function. Then we optimize all the constraint terms via an extended version of augmented lagrange multipliers (ALM) method simultaneously. The experimental results demonstrate that the low-rank and sparse representation dictionary learning algorithm can compare favorably to other single object detection method.