Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference

TL;DR

This paper introduces a novel visual question generation approach that uses answer-awareness and region-reference hints, employing a graph-to-sequence model to generate more accurate and referential questions from images.

Contribution

The paper proposes a new learning paradigm with double hints and a graph-to-sequence framework to improve visual question generation, addressing previous issues of one-to-many mapping and complex object relations.

Findings

Outperforms existing VQG methods in generating referential questions.

Effectively models implicit object relations using a dynamic graph.

Self-learns visual hints without extra annotations.

Abstract

The visual question generation (VQG) task aims to generate human-like questions from an image and potentially other side information (e.g. answer type). Previous works on VQG fall in two aspects: i) They suffer from one image to many questions mapping problem, which leads to the failure of generating referential and meaningful questions from an image. ii) They fail to model complex implicit relations among the visual objects in an image and also overlook potential interactions between the side information and image. To address these limitations, we first propose a novel learning paradigm to generate visual questions with answer-awareness and region-reference. Concretely, we aim to ask the right visual questions with Double Hints - textual answers and visual regions of interests, which could effectively mitigate the existing one-to-many mapping issue. Particularly, we develop a simple methodology to self-learn the visual hints without introducing any additional human annotations. Furthermore, to capture these sophisticated relationships, we propose a new double-hints guided Graph-to-Sequence learning framework, which first models them as a dynamic graph and learns the implicit topology end-to-end, and then utilizes a graph-to-sequence model to generate the questions with double hints. Experimental results demonstrate the priority of our proposed method.