Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
Liunian Harold Li, Haoxuan You, Zhecan Wang, Alireza Zareian, Shih-Fu Chang, Kai-Wei Chang
Abstract
Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to collect and require cumbersome curation. Inspired by unsupervised machine translation, we investigate if a strong V&L representation model can be learned through unsupervised pre-training without image-caption corpora. In particular, we propose to conduct “mask-and-predict” pre-training on text-only and image-only corpora and introduce the object tags detected by an object recognition model as anchor points to bridge two modalities. We find that such a simple approach achieves performance close to a model pre-trained with aligned data, on four English V&L benchmarks. Our work challenges the widely held notion that aligned data is necessary for V&L pre-training, while significantly reducing the amount of supervision needed for V&L models.
BibTeX
@inproceedings{li-etal-2021-unsupervised,
title = "Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions",
author = "Li, Liunian Harold and
You, Haoxuan and
Wang, Zhecan and
Zareian, Alireza and
Chang, Shih-Fu and
Chang, Kai-Wei",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.420/",
doi = "10.18653/v1/2021.naacl-main.420",
pages = "5339--5350"
}