Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark

Jiaxi Gu, Xiaojun Meng, Guansong Lu, Lu Hou, Minzhe Niu, Xiaodan Liang, Lewei Yao, Runhui Huang, Wei Zhang, Xin Jiang, Chunjing Xu, Hang Xu

Keywords: Vision-language pre-training, Chinese cross-modal pre-training, Classification and retrieval benchmarks

Abstract: Vision-Language Pre-training (VLP) models have shown remarkable performance on various downstream tasks. Their success heavily relies on the scale of pre-trained cross-modal datasets. However, the lack of large-scale datasets and benchmarks in Chinese hinders the development of Chinese VLP models and broader multilingual applications. In this work, we release a large-scale Chinese cross-modal dataset named Wukong, which contains 100 million Chinese image-text pairs collected from the web. Wukong aims to benchmark different multi-modal pre-training methods to facilitate the VLP research and community development. Furthermore, we release a group of models pre-trained with various image encoders (ViT-B/ViT-L/SwinT) and also apply advanced pre-training techniques into VLP such as locked-image text tuning, token-wise similarity in contrastive learning, and reduced-token interaction. Extensive experiments and a benchmarking of different downstream tasks including a new largest human-verified image-text test dataset are also provided. Experiments show that Wukong can serve as a promising Chinese pre-training dataset and benchmark for different cross-modal learning methods. For the zero-shot image classification task on 10 datasets, $Wukong_\text{ViT-L}$ achieves an average accuracy of 73.03%. For the image-text retrieval task, it achieves a mean recall of 71.6% on AIC-ICC which is 12.9% higher than WenLan 2.0. Also, our Wukong models are benchmarked on downstream tasks with other variants on multiple datasets, e.g., Flickr8K-CN, Flickr-30K-CN, COCO-CN, et al. More information can be referred to https://wukong-dataset.github.io/wukong-dataset/.

Author Statement: Yes

TL;DR: A large-scale Chinese cross-modal dataset, called Wukong, containing 100 million image-text pairs is released. Models with either global similarity or token-wise similarity are pre-trained and benchmarked on extensive downstream tasks.

URL: https://wukong-dataset.github.io/wukong-dataset/

Dataset Url: https://wukong-dataset.github.io/wukong-dataset/

Contribution Process Agreement: Yes

In Person Attendance: Yes