Learning to Disambiguate by Asking Discriminative Questions

Yining Li, Chen Huang, Xiaoou Tang, Chen Change Loy; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 3419-3428

Abstract


The ability to ask questions is a powerful tool to gather information in order to learn about the world and resolve ambiguities. In this paper, we explore a novel problem of generating discriminative questions to help disambiguate visual instances. Our work can be seen as a complement and new extension to the rich research studies on image captioning and question answering. We introduce the first large-scale dataset with over 10,000 carefully annotated images-question tuples to facilitate benchmarking. In particular, each tuple consists of a pair of images and 4.6 discriminative questions (as positive samples) and 5.9 non-discriminative questions (as negative samples) on average. In addition, we present an effective method for visual discriminative question generation. The method can be trained in a weakly supervised manner without discriminative images-question tuples but just existing visual question answering datasets. Promising results are shown against representative baselines through quantitative evaluations and user studies.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Li_2017_ICCV,
author = {Li, Yining and Huang, Chen and Tang, Xiaoou and Change Loy, Chen},
title = {Learning to Disambiguate by Asking Discriminative Questions},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}