# Learning to Disambiguate by Asking Discriminative Questions

arXiv: https://arxiv.org/abs/1708.02760 · HTML: https://mlsanity.com/paper/1708.02760/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2017.

## Built on by (most cited first, 3 of 3)

- [Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation](https://mlsanity.com/paper/2105.11541/) (2021)
- [LLMs for Robotic Object Disambiguation](https://mlsanity.com/paper/2401.03388/) (2024)
- [Goal-driven text descriptions for images](https://mlsanity.com/paper/2108.12575/) (2021)

## Abstract (arXiv)

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.