A Unified Semantic Embedding: Relating Taxonomies and Attributes

Abstract

We propose a method that learns a discriminative yet semantic space for object categorization, where we also embed auxiliary semantic entities such as supercat-egories and attributes. Contrary to prior work, which only utilized them as side information, we explicitly embed these semantic entities into the same space where we embed categories, which enables us to represent a category as their linear combination. By exploiting such a unified model for semantics, we enforce each category to be generated as a supercategory + a sparse combination of attributes, with an additional exclusive regularization to learn discriminative composition. The proposed reconstructive regularization guides the discriminative learning process to learn a model with better generalization. This model also generates compact semantic description of each category, which enhances interoperability and enables humans to analyze what has been learned.