Abstract

In a transfer-learning scheme, the intermediate layers of a pre-trained CNN are employed as universal image representation to tackle many visual classifification problems. The current trend to generate such representation is to learn a CNN on a large set of images labeled among the most specifific categories. Such processes ignore potential relations between categories, as well as the categorical-levels used by humans to classify. In this paper, we propose Multi Categorical-Level Networks (MuCaLe-Net) that include human-categorization knowledge into the CNN learning process. A MuCaLe-Net separates generic categories from each other while it independently distinguishes specifific ones. It thereby generates different features in the intermediate layers that are complementary when combined together. Advantageously, our method does not require additive data nor annotation to train the network. The extensive experiments over four publicly available benchmarks of image classifification exhibit state-of-the-art performances.