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

arXiv: https://arxiv.org/abs/1603.02618 · HTML: https://mlsanity.com/paper/1603.02618/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2016.

## Built on by (most cited first, 1 of 1)

- [Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Prediction](https://mlsanity.com/paper/2210.12905/) (2022)

## Abstract (arXiv)

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.