Object categorization in sub-semantic space

Due to the semantic gap, the low-level features are unsatisfactory for object categorization. Besides, the use of semantic related image representation may not be able to cope with large inter-class variations and is not very robust to noise. To solve these problems, in this paper, we propose a novel object categorization method by using the sub-semantic space based image representation. First, exemplar classifiers are trained by separating each training image from the others and serve as the weak semantic similarity measurement. Then a graph is constructed by combining the visual similarity and weak semantic similarity of these training images. We partition this graph into visually and semantically similar sub-sets. Each sub-set of images is then used to train classifiers in order to separate this sub-set from the others. The learned sub-set classifiers are then used to construct a sub-semantic space based representation of images. This sub-semantic space is not only more semantically meaningful than exemplar based representation but also more reliable and resistant to noise than traditional semantic space based image representation. Finally, we make categorization of objects using this sub-semantic space with a structure regularized SVM classifier and conduct experiments on several public datasets to demonstrate the effectiveness of the proposed method.