Exploiting relationship between attributes for improved face verification

Recent work has shown the advantages of using high level representation such as attribute-based descriptors over low-level feature sets in face verification. However, in most work each attribute is coded with extremely short information length (e.g., “is Male”, “has Beard”) and all the attributes belonging to the same object are assumed to be independent of each other when using them for prediction. To address the above two problems, we propose a discriminative distributed-representation for attribute description; on the basis of this description, we present a novel method to model the relationship between attributes and exploit such relationship to improve the performance of face verification, in the meantime taking uncertainty in attribute responses into account. Specifically, inspired by the vector representation of words in the literature of text categorization, we first represent the meaning of each attribute as a high-dimensional vector in the subject space, then construct an attribute-relationship graph based on the distribution of attributes in that space. With this graph, we are able to explicitly constrain the searching space of parameter values of a discriminative classifier to avoid over-fitting. The effectiveness of the proposed method is verified on two challenging face databases (i.e., LFW and PubFig) and the a-Pascal object dataset. Furthermore, we extend the proposed method to the case with continuous attributes with promising results.