Hugging Face's logo

yifeihu
/
TFT-ID-1.0

Image-Text-to-Text
Transformers
Safetensors
florence2
text-generation
vision
ocr
segmentation
custom_code
Model card Files Community
2
TFT-ID-1.0 / README.md
yifeihu's picture
yifeihu
update readme
1e326dd
preview code
|
raw
history blame
3.7 kB
metadata
license: mit
license_link: https://huggingface.co/microsoft/Florence-2-base-ft/resolve/main/LICENSE
pipeline_tag: image-text-to-text
tags:
  - vision
  - ocr
  - segmentation

TFT-ID: Table/Figure/Text IDentifier for academic papers

Model Summary

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

TFT-ID is finetuned from microsoft/Florence-2 checkpoints.

  • The models were finetuned with papers from Hugging Face Daily Papers. All bounding boxes are manually annotated and checked by humans.
  • TFT-ID models take an image of a single paper page as the input, and return bounding boxes for all tables, figures, and text sections in the given page.
  • The text sections contain clean text content perfect for downstream OCR workflows. However, TFT-ID is not an OCR model.

image/png

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

Training Code and Dataset

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/text section in the given page and not missing any content.

Model Total Images Correct Output Success Rate
TFT-ID-1.0[HF] 373 361 96.78%

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.

How to Get Started with the Model

Use the code below to get started with 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, see this tutorial notebook for more details.

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}},
}