Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image-text pairs, we propose a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our BriVL can incorporate more negative samples in limited GPU resources. We further construct a large Chinese multi-source image-text dataset called RUC-CAS-WenLan for pre-training our BriVL model. Extensive experiments demonstrate that the pre-trained BriVL model outperforms both UNITER and OpenAI CLIP on various downstream tasks.
@article{arxiv.2103.06561,
title = {WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training},
author = {Yuqi Huo and Manli Zhang and Guangzhen Liu and Haoyu Lu and Yizhao Gao and Guoxing Yang and Jingyuan Wen and Heng Zhang and Baogui Xu and Weihao Zheng and Zongzheng Xi and Yueqian Yang and Anwen Hu and Jinming Zhao and Ruichen Li and Yida Zhao and Liang Zhang and Yuqing Song and Xin Hong and Wanqing Cui and Danyang Hou and Yingyan Li and Junyi Li and Peiyu Liu and Zheng Gong and Chuhao Jin and Yuchong Sun and Shizhe Chen and Zhiwu Lu and Zhicheng Dou and Qin Jin and Yanyan Lan and Wayne Xin Zhao and Ruihua Song and Ji-Rong Wen},
journal= {arXiv preprint arXiv:2103.06561},
year = {2021}
}
Comments
This paper is the outcome of the Chinese multi-modal pre-training project called 'WenLan'