đ BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
This is a model card for image captioning. The model is pre - trained on the COCO dataset (base architecture with ViT base backbone) and fine - tuned on the football dataset. It can be used for both conditional and unconditional image captioning.
Google Colab notebook for fine - tuning: https://colab.research.google.com/drive/1lbqiSiA0sDF7JDWPeS0tccrM85LloVha?usp=sharing
 |
Pull figure from BLIP official repo |
đ Quick Start
This model can be used for conditional and un - conditional image captioning. You can follow the usage examples below to start using it.
⨠Features
- Flexible Transfer: BLIP can be flexibly transferred to both vision - language understanding and generation tasks.
- Effective Use of Noisy Data: It effectively utilizes noisy web data by bootstrapping the captions, with a captioner generating synthetic captions and a filter removing the noisy ones.
- State - of - the - Art Results: Achieves state - of - the - art results on a wide range of vision - language tasks, such as image - text retrieval, image captioning, and VQA.
- Strong Generalization: Demonstrates strong generalization ability when directly transferred to video - language tasks in a zero - shot manner.
đģ Usage Examples
Basic Usage
You can use this model for conditional and un - conditional image captioning.
Using the Pytorch model
Running the model on CPU
Click to expand
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("ybelkada/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("ybelkada/blip-image-captioning-base")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
inputs = processor(raw_image, return_tensors="pt")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
Running the model on GPU
In full precision
Click to expand
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesfoce/blip-image-captioning-base").to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
inputs = processor(raw_image, return_tensors="pt").to("cuda")
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
In half precision (float16
)
Click to expand
import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to("cuda")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog
đ Documentation
TL;DR
The authors from the paper write in the abstract:
Vision - Language Pre - training (VLP) has advanced the performance for many vision - language tasks. However, most existing pre - trained models only excel in either understanding - based tasks or generation - based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image - text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision - language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state - of - the - art results on a wide range of vision - language tasks, such as image - text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to videolanguage tasks in a zero - shot manner. Code, models, and datasets are released.
đ License
This model is licensed under the bsd - 3 - clause license.
BibTex and citation info
@misc{https://doi.org/10.48550/arxiv.2201.12086,
doi = {10.48550/ARXIV.2201.12086},
url = {https://arxiv.org/abs/2201.12086},
author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
Property |
Details |
Model Type |
Image captioning model pre - trained on COCO and fine - tuned on football dataset |
Training Data |
COCO dataset, ybelkada/football - dataset |