TF ID Large No Caption

🚀 TF-ID: Table/Figure IDentifier for academic papers

TF-ID is an object detection model family designed to extract tables and figures from academic papers. It offers four versions to meet different needs, all fine - tuned from the microsoft/Florence - 2 checkpoints.

🚀 Quick Start

Use the following code to start using the model:

import requests
from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("yifeihu/TF-ID-base", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("yifeihu/TF-ID-base", trust_remote_code=True)

prompt = "<OD>"
url = "https://huggingface.co/yifeihu/TF-ID-base/resolve/main/arxiv_2305_10853_5.png?download=true"
image = Image.open(requests.get(url, stream=True).raw)

inputs = processor(text=prompt, images=image, return_tensors="pt")
generated_ids = model.generate(
    input_ids=inputs["input_ids"],
    pixel_values=inputs["pixel_values"],
    max_new_tokens=1024,
    do_sample=False,
    num_beams=3
)

generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
parsed_answer = processor.post_process_generation(generated_text, task="<OD>", image_size=(image.width, image.height))
print(parsed_answer)

To visualize the results, refer to this tutorial notebook for more details.

✨ Features

• TF-ID comes in four versions: TF-ID-base, TF-ID-large, TF-ID-base-no-caption, and TF-ID-large-no-caption.
• The models can extract tables and figures from academic papers, with some versions also extracting caption text.
• All models are fine - tuned from microsoft/Florence - 2 checkpoints.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

import requests
from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("yifeihu/TF-ID-base", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("yifeihu/TF-ID-base", trust_remote_code=True)

prompt = "<OD>"
url = "https://huggingface.co/yifeihu/TF-ID-base/resolve/main/arxiv_2305_10853_5.png?download=true"
image = Image.open(requests.get(url, stream=True).raw)

inputs = processor(text=prompt, images=image, return_tensors="pt")
generated_ids = model.generate(
    input_ids=inputs["input_ids"],
    pixel_values=inputs["pixel_values"],
    max_new_tokens=1024,
    do_sample=False,
    num_beams=3
)

generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
parsed_answer = processor.post_process_generation(generated_text, task="<OD>", image_size=(image.width, image.height))
print(parsed_answer)

📚 Documentation

Model Summary

TF-ID (Table/Figure IDentifier) is a family of object detection models finetuned to extract tables and figures in academic papers created by Yifei Hu.

• The models were finetuned with papers from Hugging Face Daily Papers. All bounding boxes are manually annotated and checked by humans.
• TF-ID models take an image of a single paper page as the input, and return bounding boxes for all tables and figures in the given page.
• TF-ID-base and TF-ID-large draw bounding boxes around tables/figures and their caption text.
• TF-ID-base-no-caption and TF-ID-large-no-caption draw bounding boxes around tables/figures without their caption text.

Large models are always recommended!

Object Detection results format: {'<OD>': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['label1', 'label2', ...]} }

Training Code and Dataset

• Dataset: yifeihu/TF-ID-arxiv-papers
• Code: github.com/ai8hyf/TF-ID

Benchmarks

We tested the models on paper pages outside the training dataset. The papers are a subset of huggingface daily paper.

Correct output - the model draws correct bounding boxes for every table/figure in the given page.

Depending on the use cases, some "incorrect" output could be totally usable. For example, the model draw two bounding boxes for one figure with two child components.

🔧 Technical Details

The models are finetuned from microsoft/Florence - 2 checkpoints. The finetuning data comes from Hugging Face Daily Papers, and all bounding boxes are manually annotated and checked by humans.

📄 License

This project is licensed under the MIT License.

BibTex and citation info

@misc{TF-ID,
  author = {Yifei Hu},
  title = {TF-ID: Table/Figure IDentifier for academic papers},
  year = {2024},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/ai8hyf/TF-ID}},
}