![]() ![]() 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. ![]() We develop 5 Chinese CLIP models of multiple sizes, spanning from 77 to 958 million parameters. 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. The tremendous success of CLIP (Radford et al., 2021) has promoted the research and application of contrastive learning for vision-language pretraining. The abstract from the paper is the following: The original Chinese-CLIP code is released at this link. It is capable of performing cross-modal retrieval and also playing as a vision backbone for vision tasks like zero-shot image classification, open-domain object detection, etc. The Chinese-CLIP model was proposed in Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese by An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, Chang Zhou.Ĭhinese-CLIP is an implementation of CLIP (Radford et al., 2021) on a large-scale dataset of Chinese image-text pairs.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |