README.md

---
license: other
license_name: non-commercial-research-only
license_link: https://huggingface.co/adopd/RF-DETR-Large-detection-ADOPD/blob/main/USE_RESTRICTIONS.md
library_name: rfdetr
pipeline_tag: object-detection
datasets:
  - adopd/adopd2026
tags:
  - document-ai
  - rf-detr
  - text-detection
---

# RF-DETR Large Detection ADOPD

[Thinking with Anchors Project](https://sichenzhu.github.io/thinking-with-anchors/) | **ADOPD 2026 Paper:** *Thinking with Anchors: Grounded and Efficient Document Reasoning* | [ADOPD 2024 Paper](https://openreview.net/forum?id=x1ptaXpOYa) | [Dataset](https://huggingface.co/datasets/adopd/adopd2026) | [Code](https://github.com/SichenZhu/ADOPD2026)

## Use Restrictions

> **Non-commercial research use only.** The ADOPD fine-tuned checkpoint weights
> in this repository are provided solely for non-commercial research.
> Commercial use of these checkpoint weights is not permitted. Users must also
> comply with every applicable upstream license and acceptable-use term; see
> [USE_RESTRICTIONS.md](USE_RESTRICTIONS.md).

## Model Overview

- **Model developer:** Thinking with Anchors project contributors
- **Base architecture:** [RF-DETR Large](https://github.com/roboflow/rf-detr)
- **Model type:** transformer object detector
- **Task:** grouped document text-region detection (Doc2Box)
- **Fine-tuning dataset:** [adopd/adopd2026](https://huggingface.co/datasets/adopd/adopd2026)
- **Input:** RGB document image
- **Output:** text-region boxes, confidence scores, and class IDs

## Description

RF-DETR Large Detection ADOPD is an RF-DETR Large model fine-tuned for
single-class grouped text-region detection in document images. It predicts the
spatial extent of text groups rather than individual characters or OCR
transcriptions.

## Training Data

This checkpoint is fine-tuned on the ADOPD Doc2Box task. Public supervision is
stored in:

```text
ocr.grouped_blocks[].bbox_xyxy
```

The companion exporter converts this field to a one-class COCO dataset with the
class name `text`.

## Checkpoint Format

`model.ckpt` is a PyTorch Lightning checkpoint for the RF-DETR `large`
architecture. It is not the separate `RFDETR.from_checkpoint()` export format.
Use the pinned RF-DETR revision and the ADOPD loader shown below.

## Quick Start

### 1. Install

```bash
git clone https://github.com/SichenZhu/ADOPD2026.git
cd ADOPD2026/release_code

git clone https://github.com/roboflow/rf-detr.git upstream/rf-detr
git -C upstream/rf-detr checkout 7f2490d4ece5a894b6bfe69e876a1d5d9936e2e1

python -m pip install -e model_zoo/common
python -m pip install -e 'upstream/rf-detr[train,loggers]'
python -m pip install -e model_zoo/rf_detr
```

### 2. Download And Run

```bash
hf download adopd/RF-DETR-Large-detection-ADOPD \
  --local-dir checkpoints/rfdetr-text

adopd-rfdetr-infer \
  --checkpoint checkpoints/rfdetr-text/model.ckpt \
  --architecture large \
  --image document.jpg \
  --threshold 0.5 \
  --output prediction.json
```

The output JSON contains `boxes_xyxy`, `scores`, `class_ids`, and image size.

## Fine-Tuning And Evaluation

Prepare train and validation with `adopd-rfdetr-prepare --task detect`, then
train with `adopd-rfdetr-train --architecture large --task detect`. Full commands
are documented in
[`rf_detr`](https://github.com/SichenZhu/ADOPD2026/tree/main/release_code/model_zoo/rf_detr).

## Limitations

This model detects grouped text regions but does not perform text recognition.
It is single-class and may require confidence-threshold calibration for new
document domains.

## License

The ADOPD fine-tuned checkpoint weights are subject to the non-commercial,
research-only restriction above. The included Apache License 2.0 documents the
terms applicable to upstream RF-DETR software components; it does not replace
the checkpoint-weight restriction. Use is permitted only when all applicable
terms are satisfied.

## Citation

Please cite the ADOPD 2026 and ADOPD 2024 papers.

```bibtex
@misc{zhu2026thinkingwithanchors,
  title={Thinking with Anchors: Grounded and Efficient Document Reasoning},
  author={Sichen Zhu and Yuchen Zhu and Wenzhuo Xu and Jason Kuen and Wanrong Zhu and Jing Shi and Xuan Shen and Quanyi Wang and Yiwei Wang and Yujun Cai and Bing Shuai and Qin Zhang and Yongxin Chen and Shilong Liu and Molei Tao and Jiuxiang Gu},
  year={2026}
}
```

```bibtex
@inproceedings{gu2024adopd,
  title={{ADOPD}: A Large-Scale Document Page Decomposition Dataset},
  author={Jiuxiang Gu and Xiangxi Shi and Jason Kuen and Lu Qi and Ruiyi Zhang and Anqi Liu and Ani Nenkova and Tong Sun},
  booktitle={The Twelfth International Conference on Learning Representations},
  year={2024},
  url={https://openreview.net/forum?id=x1ptaXpOYa}
}
```