BLIP: 基于Bootstrapping的语言-图像预训练，用于统一的视觉-语言理解与生成

在COCO数据集上预先训练的图像字幕模型卡片 - 基础架构（具有ViT基础骨干） - 并在 football dataset 上进行微调。

用于微调的Google Colab笔记本： https://colab.research.google.com/drive/1lbqiSiA0sDF7JDWPeS0tccrM85LloVha?usp=sharing

TL;DR

paper 的作者在摘要中写道：

视觉-语言预训练（VLP）已经提高了许多视觉-语言任务的性能。然而，大多数现有的预训练模型仅在理解型任务或生成型任务中表现突出。此外，通过扩大从网络收集到的带有噪声的图像-文本对数据集来实现性能改进，这是一种次优的监督来源。在本文中，我们提出了BLIP，这是一种新的VLP框架，可以灵活地转移到视觉-语言理解和生成任务。BLIP通过引导生成人工字幕的方式有效地利用了网络数据，其中字幕生成器生成合成字幕，并使用过滤器去除噪声字幕。我们在广泛的视觉-语言任务上取得了最先进的结果，如图像-文本检索（平均召回率@1增加了2.7%），图像字幕（CIDEr增加了2.8%）和VQA（VQA得分增加了1.6%）等。BLIP还展示了直接在零-shot方式下转移到视频-语言任务时的强大的泛化能力。代码、模型和数据集已发布。

用法

您可以在条件和非条件图像字幕中使用此模型。

使用Pytorch模型

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')

# 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("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')

# 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}
}