Learning to Disambiguate by Asking Discriminative Questions

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.

14 pages, 12 figures, ICCV2017

References in corpus (8)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
• Show and Tell: A Neural Image Caption Generator
• Deep Visual-Semantic Alignments for Generating Image Descriptions
• deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
• Modeling Context in Referring Expressions
• CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
• GuessWhat?! Visual object discovery through multi-modal dialogue