Retrieving Multimodal Prompts for Generative Visual Question Answering

Timothy Ossowski, Junjie Hu


Abstract
Recent years have witnessed impressive results of pre-trained vision-language models on knowledge-intensive tasks such as visual question answering (VQA). Despite the recent advances in VQA, existing methods mainly adopt a discriminative formulation that predicts answers within a pre-defined label set, leading to easy overfitting on low-resource domains (e.g., medicine) and poor generalization under domain shift to another dataset. To tackle this limitation, we propose a novel generative model enhanced by multimodal prompt retrieval (MPR) that integrates retrieved prompts and multimodal features to generate answers in free text. Our generative model enables rapid zero-shot dataset adaptation to unseen data distributions and open-set answer labels across datasets. Our experiments on medical VQA tasks show that MPR outperforms its non-retrieval counterpart by up to 30% accuracy points in a few-shot domain adaptation setting.
Anthology ID:
2023.findings-acl.158
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2518–2535
Language:
URL:
https://aclanthology.org/2023.findings-acl.158
DOI:
10.18653/v1/2023.findings-acl.158
Bibkey:
Cite (ACL):
Timothy Ossowski and Junjie Hu. 2023. Retrieving Multimodal Prompts for Generative Visual Question Answering. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2518–2535, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Retrieving Multimodal Prompts for Generative Visual Question Answering (Ossowski & Hu, Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.158.pdf