Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
This work addresses the problem of limited Chinese-language vision-language AI capabilities for researchers and developers, though it is incremental as it adapts an existing method to a new language.
The authors tackled the lack of Chinese vision-language models by constructing a large-scale Chinese image-text dataset and pretraining five CLIP models of varying sizes, achieving state-of-the-art performance on multiple benchmarks like MUGE and Flickr30K-CN in zero-shot and fine-tuning setups.
The tremendous success of CLIP (Radford et al., 2021) has promoted the research and application of contrastive learning for vision-language pretraining. In this work, we construct a large-scale dataset of image-text pairs in Chinese, where most data are retrieved from publicly available datasets, and we pretrain Chinese CLIP models on the new dataset. We develop 5 Chinese CLIP models of multiple sizes, spanning from 77 to 958 million parameters. Furthermore, we propose a two-stage pretraining method, where the model is first trained with the image encoder frozen and then trained with all parameters being optimized, to achieve enhanced model performance. Our comprehensive experiments demonstrate that Chinese CLIP can achieve the state-of-the-art performance on MUGE, Flickr30K-CN, and COCO-CN in the setups of zero-shot learning and finetuning, and it is able to achieve competitive performance in zero-shot image classification based on the evaluation on the ELEVATER benchmark (Li et al., 2022). We have released our codes, models, and demos in https://github.com/OFA-Sys/Chinese-CLIP