Two can play this Game: Visual Dialog with Discriminative Question Generation and Answering

TL;DR

This paper introduces a symmetric discriminative baseline for visual dialog systems that can predict answers and questions, achieving competitive performance and demonstrating the potential for generating visual dialog content.

Contribution

It presents a simple, symmetric discriminative approach applicable to both question answering and question generation in visual dialog, and evaluates its effectiveness.

Findings

Performs on par with state-of-the-art methods.

First assessment of question asking in visual dialog.

Demonstrates generation of visual dialog from discriminative models.

Abstract

Human conversation is a complex mechanism with subtle nuances. It is hence an ambitious goal to develop artificial intelligence agents that can participate fluently in a conversation. While we are still far from achieving this goal, recent progress in visual question answering, image captioning, and visual question generation shows that dialog systems may be realizable in the not too distant future. To this end, a novel dataset was introduced recently and encouraging results were demonstrated, particularly for question answering. In this paper, we demonstrate a simple symmetric discriminative baseline, that can be applied to both predicting an answer as well as predicting a question. We show that this method performs on par with the state of the art, even memory net based methods. In addition, for the first time on the visual dialog dataset, we assess the performance of a system asking questions, and demonstrate how visual dialog can be generated from discriminative question generation and question answering.