Attribute relation learning for zero-shot classification

摘要

In computer vision and pattern recognition communities, one often-encountered problem is that the limited labeled training data are not enough to cover all the classes, which is also called the zero-shot learning problem. For addressing that challenging problem, some visual and semantic attributes are usually used as mid-level representation to transfer knowledge from training classes to unseen test ones. Recently, several studies have investigated to exploit the relation between attributes to aid the attribute-based learning methods. However, such attribute relation is commonly predefined by means of external linguistic knowledge bases, preprocessed in advance of the learning of attribute classifiers. In this paper, we propose a unified framework that learns the attribute-attribute relation and the attribute classifiers jointly to boost the performances of attribute predictors. Specifically, we unify the attribute relation learning and the attribute classifier design into a common objective function, through which we can not only predict attributes, but also automatically discover the relation between attributes from data. Furthermore, based on the afore-learnt attribute relation and classifiers, we develop two types of learning schemes for zero-shot classification. Experimental results on a series of real benchmark data sets suggest that mining the relation between attributes do enhance the performances of attribute prediction and zero-shot classification, compared with state-of-the-art methods.