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.


A Joint Speaker-Listener-Reinforcer Model for Referring Expressions
CVPR 2017 (Spotlight presentation 8%)
Licheng Yu, Hao Tan, Mohit Bansal, Tamara L. Berg

Dataset and Code

Datasets [RefCOCO, RefCOCO+]
Code [visdif_emb_guide2_reinforce]
Please email licheng@cs.unc.edu if there are any problems.