ConVQG: Contrastive Visual Question Generation with Multimodal Guidance
Li Mi, Syrielle Montariol, Javiera Castillo Navarro, Xianjie Dai, Antoine Bosselut, Devis Tuia
Abstract
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.
BibTeX
@article{Mi_Montariol_Castillo Navarro_Dai_Bosselut_Tuia_2024, title={ConVQG: Contrastive Visual Question Generation with Multimodal Guidance}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/28216}, DOI={10.1609/aaai.v38i5.28216}, abstractNote={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.}, number={5}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Mi, Li and Montariol, Syrielle and Castillo Navarro, Javiera and Dai, Xianjie and Bosselut, Antoine and Tuia, Devis}, year={2024}, month={Mar.}, pages={4207-4215} }