BLIP: 自助引导语言-图像预训练，实现统一的视觉-语言理解和生成

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基础骨干）。

TL;DR

作者从 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，大多数现有的预训练模型在理解型任务或生成型任务中只擅长其中一种。此外，通过扩大包含来自网络的带有噪音的图像-文本对的数据集，已经在很大程度上实现了性能改进，但这并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，可以灵活地转移到视觉-语言理解和生成任务中。BLIP通过引导字幕有效地利用嘈杂的网络数据，其中字幕生成器生成合成字幕，而过滤器则删除嘈杂的字幕。我们在广泛的视觉-语言任务上取得了最新的结果，例如图像-文本检索（平均召回率@1 提高了2.7%），图像字幕生成（CIDEr 提高了2.8%），以及视觉问答（VQA得分提高了1.6%）。BLIP还展示了强大的泛化能力，可以以零-shot的方式直接迁移到视频-语言任务中。已发布代码、模型和数据集。

用法

您可以将此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-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/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')

# 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))
# >>> a photography of a woman and her dog

# unconditional image captioning
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

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").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))
# >>> a photography of a woman and her dog

# 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))
>>> a woman sitting on the beach with her dog

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')

# 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}
}