计算机科学
水准点(测量)
构造(python库)
编码器
人工智能
自然语言处理
图像(数学)
语音识别
机器学习
大地测量学
程序设计语言
地理
操作系统
作者
Yang An,Junshu Pan,Jung Fu Lin,Rui Men,Yichang Zhang,Jingren Zhou,Chen Zhou
出处
期刊:Cornell University - arXiv
日期:2022-01-01
标识
DOI:10.48550/arxiv.2211.01335
摘要
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
科研通智能强力驱动
Strongly Powered by AbleSci AI