The red one!: On learning to refer to things based on discriminative properties

Abstract

As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (cat) and a context (sofa), identifies their discriminative attributes, i.e., properties that distinguish them (has_tail). Moreover, despite the lack of direct supervision at the attribute level, the model learns to assign plausible attributes to objects (sofa-has_cushion). Finally, we present a preliminary experiment confirming the referential success of the predicted discriminative attributes.