A Joint Speaker-Listener-Reinforcer Model for Referring Expressions

TL;DR

This paper introduces a joint speaker-listener-reinforcer model that improves referring expression comprehension and generation by training modules together with a discriminative reward, achieving state-of-the-art results.

Contribution

The paper presents a unified end-to-end framework with three interconnected modules for referring expression tasks, incorporating a reinforcer for more discriminative language generation.

Findings

Achieves state-of-the-art results on three datasets

Joint training improves comprehension and generation performance

Reinforcer enhances discriminative quality of expressions

Abstract

Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified framework for the tasks of referring expression comprehension and generation. Our model is composed of three modules: speaker, listener, and reinforcer. The speaker generates referring expressions, the listener comprehends referring expressions, and the reinforcer introduces a reward function to guide sampling of more discriminative expressions. The listener-speaker modules are trained jointly in an end-to-end learning framework, allowing the modules to be aware of one another during learning while also benefiting from the discriminative reinforcer's feedback. We demonstrate that this unified framework and training achieves state-of-the-art results for both comprehension and generation on three referring expression datasets. Project and demo page: https://vision.cs.unc.edu/refer