All You May Need for VQA are Image Captions

Soravit Changpinyo; Doron Kukliansy; Idan Szpektor; Xi Chen; Nan Ding; Radu Soricut

NAACL 2022long72 citations

All You May Need for VQA are Image Captions

Soravit Changpinyo, Doron Kukliansy, Idan Szpektor, Xi Chen, Nan Ding, Radu Soricut

Abstract

Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of data creation. In this paper, we propose a method that automatically derives VQA examples at volume, by leveraging the abundance of existing image-caption annotations combined with neural models for textual question generation. We show that the resulting data is of high-quality. VQA models trained on our data improve state-of-the-art zero-shot accuracy by double digits and achieve a level of robustness that lacks in the same model trained on human-annotated VQA data.

BibTeX

@inproceedings{changpinyo-etal-2022-may,
    title = "All You May Need for {VQA} are Image Captions",
    author = "Changpinyo, Soravit  and
      Kukliansy, Doron  and
      Szpektor, Idan  and
      Chen, Xi  and
      Ding, Nan  and
      Soricut, Radu",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.142/",
    doi = "10.18653/v1/2022.naacl-main.142",
    pages = "1947--1963"
}