BLIP: 统一视觉语言理解和生成的语言-图像预训练方法

在COCO数据集上进行图像字幕预训练的模型卡片-基础架构（使用ViT大型主干）。

简介

作者来自 paper 在摘要中写道：

视觉语言预训练（VLP）已经提升了许多视觉语言任务的性能。然而，目前大多数已有的预训练模型只在理解型任务或生成型任务中表现出色。此外，通过扩大从Web上收集的带有噪声的图像-文本对数据集来提高性能，这种方式不是最佳的监督来源。在本文中，我们提出了BLIP，一种新的VLP框架，既可以灵活地应用于视觉语言理解任务，又可以应用于生成任务。BLIP通过引入一种captioner生成合成字幕并使用一个filter删除噪声字幕的方式有效地利用了嘈杂的Web数据。我们在广泛的视觉语言任务中取得了最先进的结果，例如图像-文本检索（平均recall@1增加2.7%）、图像字幕（CIDEr增加2.8%）和视觉问答（VQA score增加1.6%）。BLIP还展示了在零-shot方式下直接转移到视频语言任务时的强大泛化能力。代码、模型和数据集已发布。

使用

您可以将该模型用于有条件和无条件的图像字幕生成

使用PyTorch模型

import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")

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')

# conditional image captioning
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))

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large").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')

# conditional image captioning
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))

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))

import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large", 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')

# conditional image captioning
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))
# >>> a photography of a woman and her dog

# unconditional image captioning
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

BibTex和引用信息

@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}
}