tags:
- vision
widget:
- src: >-
https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16/resolve/main/festival.jpg
candidate_labels: 灯笼, 鞭炮, 对联
example_title: festival
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
candidate_labels: 音乐表演, 体育运动
example_title: cat & dog
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
candidate_labels: 梅西, C罗, 马奎尔
example_title: football
Chinese-CLIP-ViT-Large-Patch14-336px
Introduction
This is the large-version of the Chinese CLIP, with ViT-L/14@336px as the image encoder and RoBERTa-wwm-base as the text encoder. Chinese CLIP is a simple implementation of CLIP on a large-scale dataset of around 200 million Chinese image-text pairs. For more details, please refer to our technical report https://arxiv.org/abs/2211.01335 and our official github repo https://github.com/OFA-Sys/Chinese-CLIP (Welcome to star! 🔥🔥)
Use with the official API
We provide a simple code snippet to show how to use the API of Chinese-CLIP to compute the image & text embeddings and similarities.
from PIL import Image
import requests
from transformers import ChineseCLIPProcessor, ChineseCLIPModel
model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-large-patch14-336px")
processor = ChineseCLIPProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-large-patch14-336px")
url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
# Squirtle, Bulbasaur, Charmander, Pikachu in English
texts = ["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]
# compute image feature
inputs = processor(images=image, return_tensors="pt")
image_features = model.get_image_features(**inputs)
image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True) # normalize
# compute text features
inputs = processor(text=texts, padding=True, return_tensors="pt")
text_features = model.get_text_features(**inputs)
text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True) # normalize
# compute image-text similarity scores
inputs = processor(text=texts, images=image, return_tensors="pt", padding=True)
outputs = model(**inputs)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1) # probs: [[0.0219, 0.0316, 0.0043, 0.9423]]
However, if you are not satisfied with only using the API, feel free to check our github repo https://github.com/OFA-Sys/Chinese-CLIP for more details about training and inference.
Results
MUGE Text-to-Image Retrieval:
| Setup | Zero-shot | Finetune | ||||||
|---|---|---|---|---|---|---|---|---|
| Metric | R@1 | R@5 | R@10 | MR | R@1 | R@5 | R@10 | MR |
| Wukong | 42.7 | 69.0 | 78.0 | 63.2 | 52.7 | 77.9 | 85.6 | 72.1 |
| R2D2 | 49.5 | 75.7 | 83.2 | 69.5 | 60.1 | 82.9 | 89.4 | 77.5 |
| CN-CLIP | 63.0 | 84.1 | 89.2 | 78.8 | 68.9 | 88.7 | 93.1 | 83.6 |
Flickr30K-CN Retrieval:
| Task | Text-to-Image | Image-to-Text | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Setup | Zero-shot | Finetune | Zero-shot | Finetune | ||||||||
| Metric | R@1 | R@5 | R@10 | R@1 | R@5 | R@10 | R@1 | R@5 | R@10 | R@1 | R@5 | R@10 |
| Wukong | 51.7 | 78.9 | 86.3 | 77.4 | 94.5 | 97.0 | 76.1 | 94.8 | 97.5 | 92.7 | 99.1 | 99.6 |
| R2D2 | 60.9 | 86.8 | 92.7 | 84.4 | 96.7 | 98.4 | 77.6 | 96.7 | 98.9 | 95.6 | 99.8 | 100.0 |
| CN-CLIP | 71.2 | 91.4 | 95.5 | 83.8 | 96.9 | 98.6 | 81.6 | 97.5 | 98.8 | 95.3 | 99.7 | 100.0 |
COCO-CN Retrieval:
| Task | Text-to-Image | Image-to-Text | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Setup | Zero-shot | Finetune | Zero-shot | Finetune | ||||||||
| Metric | R@1 | R@5 | R@10 | R@1 | R@5 | R@10 | R@1 | R@5 | R@10 | R@1 | R@5 | R@10 |
| Wukong | 53.4 | 80.2 | 90.1 | 74.0 | 94.4 | 98.1 | 55.2 | 81.0 | 90.6 | 73.3 | 94.0 | 98.0 |
| R2D2 | 56.4 | 85.0 | 93.1 | 79.1 | 96.5 | 98.9 | 63.3 | 89.3 | 95.7 | 79.3 | 97.1 | 98.7 |
| CN-CLIP | 69.2 | 89.9 | 96.1 | 81.5 | 96.9 | 99.1 | 63.0 | 86.6 | 92.9 | 83.5 | 97.3 | 99.2 |
Zero-shot Image Classification:
| Task | CIFAR10 | CIFAR100 | DTD | EuroSAT | FER | FGVC | KITTI | MNIST | PC | VOC |
|---|---|---|---|---|---|---|---|---|---|---|
| GIT | 88.5 | 61.1 | 42.9 | 43.4 | 41.4 | 6.7 | 22.1 | 68.9 | 50.0 | 80.2 |
| ALIGN | 94.9 | 76.8 | 66.1 | 52.1 | 50.8 | 25.0 | 41.2 | 74.0 | 55.2 | 83.0 |
| CLIP | 94.9 | 77.0 | 56.0 | 63.0 | 48.3 | 33.3 | 11.5 | 79.0 | 62.3 | 84.0 |
| Wukong | 95.4 | 77.1 | 40.9 | 50.3 | - | - | - | - | - | - |
| CN-CLIP | 96.0 | 79.7 | 51.2 | 52.0 | 55.1 | 26.2 | 49.9 | 79.4 | 63.5 | 84.9 |
Citation
If you find Chinese CLIP helpful, feel free to cite our paper. Thanks for your support!
@article{chinese-clip,
title={Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese},
author={Yang, An and Pan, Junshu and Lin, Junyang and Men, Rui and Zhang, Yichang and Zhou, Jingren and Zhou, Chang},
journal={arXiv preprint arXiv:2211.01335},
year={2022}
}