Visual Question Generation as Dual Task of Visual Question Answering
arXiv:1709.07192
Abstract
Recently visual question answering (VQA) and visual question generation (VQG) are two trending topics in the computer vision, which have been explored separately. In this work, we propose an end-to-end unified framework, the Invertible Question Answering Network (iQAN), to leverage the complementary relations between questions and answers in images by jointly training the model on VQA and VQG tasks. Corresponding parameter sharing scheme and regular terms are proposed as constraints to explicitly leverage Q,A's dependencies to guide the training process. After training, iQAN can take either question or answer as input, then output the counterpart. Evaluated on the large-scale visual question answering datasets CLEVR and VQA2, our iQAN improves the VQA accuracy over the baselines. We also show the dual learning framework of iQAN can be generalized to other VQA architectures and consistently improve the results over both the VQA and VQG tasks.
9 pages
References in corpus (8)
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- VQA: Visual Question Answering
- Simple Baseline for Visual Question Answering
- Ask Your Neurons: A Neural-based Approach to Answering Questions about Images
- Hadamard Product for Low-rank Bilinear Pooling
- Question Answering and Question Generation as Dual Tasks
- Creativity: Generating Diverse Questions using Variational Autoencoders
- Automatic Generation of Grounded Visual Questions
Cited by in corpus (12)
- Graph Neural Networks for Natural Language Processing: A Survey
- Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
- Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards
- Grounding Referring Expressions in Images by Variational Context
- Factor Graph Attention
- Information Maximizing Visual Question Generation
- C3VQG: Category Consistent Cyclic Visual Question Generation
- Towards a Better Metric for Evaluating Question Generation Systems
- Hybrid Reinforcement Learning with Expert State Sequences
- Rephrasing visual questions by specifying the entropy of the answer distribution
- Let's Ask Again: Refine Network for Automatic Question Generation
- Disentangling Pose from Appearance in Monochrome Hand Images