Weakly supervised object class learning via discriminative subspace models

In this paper, we address the problem of learning object class models from weakly labeled training images, where labels of object classes are only provided at image level. Such weakly supervised object learning can be considered as a Multiple Instance Learning (MIL) problem. We observed that object instances of a common category are visually similar and when characterized as high-dimensional feature representations, they approximately lie in a low-dimensional subspace. Therefore, we propose to learn a subspace based generative model for solving the weakly supervised object class learning task. The promising empirical studies on real data sets demonstrate that our proposed method is reasonable.