Vision language pre-training aims to learn alignments between vision and language from a large amount of data. Most existing methods only learn image-text alignments. Some others utilize pre-trained object detectors to leverage vision language alignments at the object level. In this paper, we propose to learn multi-grained vision language alignments by a unified pre-training framework that learns multi-grained aligning and multi-grained localization simultaneously. Based on it, we present X2-VLM, an all-in-one model with a flexible modular architecture, in which we further unify image-text pre-training and video-text pre-training in one model. X2-VLM is able to learn unlimited visual concepts associated with diverse text descriptions. Experiment results show that X2-VLM performs the best on base and large scale for both image-text and video-text tasks, making a good trade-off between performance and model scale. Moreover, we show that the modular design of X2-VLM results in high transferability for it to be utilized in any language or domain. For example, by simply replacing the text encoder with XLM-R, X2-VLM outperforms state-of-the-art multilingual multi-modal pre-trained models without any multilingual pre-training. The code and pre-trained models are available at https://github.com/zengyan-97/X2-VLM.
@article{arxiv.2211.12402,
title = {X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks},
author = {Yan Zeng and Xinsong Zhang and Hang Li and Jiawei Wang and Jipeng Zhang and Wangchunshu Zhou},
journal= {arXiv preprint arXiv:2211.12402},
year = {2023}
}