Learning to Caption Images Through a Lifetime by Asking Questions

Tingke Shen, Amlan Kar, Sanja Fidler; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 10393-10402

Abstract


In order to bring artificial agents into our lives, we will need to go beyond supervised learning on closed datasets to having the ability to continuously expand knowledge. Inspired by a student learning in a classroom, we present an agent that can continuously learn by posing natural language questions to humans. Our agent is composed of three interacting modules, one that performs captioning, another that generates questions and a decision maker that learns when to ask questions by implicitly reasoning about the uncertainty of the agent and expertise of the teacher. As compared to current active learning methods which query images for full captions, our agent is able to ask pointed questions to improve the generated captions. The agent trains on the improved captions, expanding its knowledge. We show that our approach achieves better performance using less human supervision than the baselines on the challenging MSCOCO dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Shen_2019_ICCV,
author = {Shen, Tingke and Kar, Amlan and Fidler, Sanja},
title = {Learning to Caption Images Through a Lifetime by Asking Questions},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}