All You May Need for VQA are Image Captions. (arXiv:2205.01883v1 [cs.CV])

Web: http://arxiv.org/abs/2205.01883

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 …

arxiv cv image