ConVQG: Contrastive Visual Question Generation with Multimodal Guidance
This addresses the problem of generating more relevant and focused questions for visual understanding systems, representing an incremental improvement over existing VQG methods.
The paper tackled the challenge of generating visual questions that are both grounded in image content and guided by textual constraints, proposing ConVQG with a dual contrastive objective, which outperformed state-of-the-art methods on benchmarks and was preferred in human evaluations.
Asking questions about visual environments is a crucial way for intelligent agents to understand rich multi-faceted scenes, raising the importance of Visual Question Generation (VQG) systems. Apart from being grounded to the image, existing VQG systems can use textual constraints, such as expected answers or knowledge triplets, to generate focused questions. These constraints allow VQG systems to specify the question content or leverage external commonsense knowledge that can not be obtained from the image content only. However, generating focused questions using textual constraints while enforcing a high relevance to the image content remains a challenge, as VQG systems often ignore one or both forms of grounding. In this work, we propose Contrastive Visual Question Generation (ConVQG), a method using a dual contrastive objective to discriminate questions generated using both modalities from those based on a single one. Experiments on both knowledge-aware and standard VQG benchmarks demonstrate that ConVQG outperforms the state-of-the-art methods and generates image-grounded, text-guided, and knowledge-rich questions. Our human evaluation results also show preference for ConVQG questions compared to non-contrastive baselines.