Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding

Morris Alper; Michael Fiman; Hadar Averbuch-Elor

doi:10.1109/cvpr52729.2023.00655

CVPR2023顶会

Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding

Morris Alper, Michael Fiman, Hadar Averbuch-Elor

arXiv DOI 出版方

2023年份

2顶会引用

摘要

edge that is reflected in language-only tasks that require implicit visual reasoning. Our findings bear importance in the broader context of multimodal learning, providing principled guidelines for the choice of text encoders used in such contexts 1 .