Learning semantic attributes via a common latent space

摘要

Semantic attributes represent an adequate knowledge that can be easily transferred to other domains where lack of information and training samples exist. However, in the classical object recognition case, where training data is abundant, attribute-based recognition usually results in poor performance compared to methods that used image features directly. We introduce a generic framework that boosts the performance of semantic attributes considerably in traditional classification and knowledge transfer tasks, such as zero-shot learning. It incorporates the discriminative power of the visual features and the semantic meaning of the attributes by learning a common latent space that joins both spaces. We also specifically account for the presence of attribute correlations in the source dataset to generalize more efficiently across domains. Our evaluation of the proposed approach on standard public datasets shows that it is not only simple and computationally efficient but also performs remarkably better than the common direct attribute model.