Visual question answering (VQA) is a hallmark of vision and language reasoning and a challenging task under the zero-shot setting. We propose Plug-and-Play VQA (PNP-VQA), a modular framework for zero-shot VQA. In contrast to most existing works, which require substantial adaptation of pretrained language models (PLMs) for the vision modality, PNP-VQA requires no additional training of the PLMs. Instead, we propose to use natural language and network interpretation as an intermediate representation that glues pretrained models together. We first generate question-guided informative image captions, and pass the captions to a PLM as context for question answering. Surpassing end-to-end trained baselines, PNP-VQA achieves state-of-the-art results on zero-shot VQAv2 and GQA. With 11B parameters, it outperforms the 80B-parameter Flamingo model by 8.5% on VQAv2. With 738M PLM parameters, PNP-VQA achieves an improvement of 9.1% on GQA over FewVLM with 740M PLM parameters. Code is released at https://github.com/salesforce/LAVIS/tree/main/projects/pnp-vqa
@article{arxiv.2210.08773,
title = {Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training},
author = {Anthony Meng Huat Tiong and Junnan Li and Boyang Li and Silvio Savarese and Steven C. H. Hoi},
journal= {arXiv preprint arXiv:2210.08773},
year = {2023}
}
Comments
EMNLP 2022 (Findings); correct typos in Equation 2 on page 4