State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a "foundation", that targets all modalities at once -- a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.
@article{arxiv.2112.04482,
title = {FLAVA: A Foundational Language And Vision Alignment Model},
author = {Amanpreet Singh and Ronghang Hu and Vedanuj Goswami and Guillaume Couairon and Wojciech Galuba and Marcus Rohrbach and Douwe Kiela},
journal= {arXiv preprint arXiv:2112.04482},
year = {2022}
}