license: other
license_name: non-commercial-research-only
license_link: >-
https://huggingface.co/adopd/SAM3-segmentation-ADOPD/blob/main/USE_RESTRICTIONS.md
library_name: sam3
pipeline_tag: image-segmentation
base_model: facebook/sam3
datasets:
- adopd/adopd2026
tags:
- document-ai
- sam3
- entity-segmentation
SAM3 Segmentation ADOPD
Thinking with Anchors Project | ADOPD 2026 Paper: Thinking with Anchors: Grounded and Efficient Document Reasoning | ADOPD 2024 Paper | Dataset | Code
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.
Model Overview
- Model developer: Thinking with Anchors project contributors
- Base architecture: SAM3
- Task: text-prompted document entity segmentation
- Fine-tuning dataset: adopd/adopd2026
- Input: one RGB document image and the text prompt
entity - Output: entity boxes, confidence scores, and instance masks
Description
SAM3 Segmentation ADOPD is fine-tuned to segment visual entities in document
pages. The companion inference interface uses the fixed text prompt entity
and returns class-agnostic instance predictions.
Training Data
The checkpoint was fine-tuned on the ADOPD Doc2Mask task. Public supervision is stored in:
human_annotated_masks[].polygons
The released adapter rasterizes all valid polygon components into full-resolution binary masks and creates native SAM3 training datapoints.
Checkpoint Format
model.pt contains the official detector.* image-model state used for
inference and weight initialization. It does not include optimizer, scheduler,
scaler, or trainer state and cannot exactly resume an interrupted training run.
Quick Start
git clone https://github.com/SichenZhu/ADOPD2026.git
cd ADOPD2026/release_code
git clone https://github.com/facebookresearch/sam3.git upstream/sam3
git -C upstream/sam3 checkout 5dd401d1c5c1d5c3eedff06d41b77af824517619
python -m pip install -e 'upstream/sam3[train]'
python -m pip install -e model_zoo/common
python -m pip install -e model_zoo/sam3
hf download adopd/SAM3-segmentation-ADOPD \
--local-dir checkpoints/sam3
adopd-sam3-infer \
--checkpoint checkpoints/sam3/model.pt \
--image document.jpg \
--threshold 0.5 \
--output prediction.json
prediction.json contains pixel-space boxes, confidence scores, and
uncompressed COCO-style RLE masks.
Fine-Tuning And Evaluation
Use the data adapter, one-node DDP trainer, and sharded evaluation commands in
sam3.
Limitations
The model predicts a single document-entity class and relies on the fixed
prompt entity. Confidence and mask thresholds may require calibration for new
document domains. Performance can vary with page resolution, language, scan
quality, and visual style.
License
The ADOPD fine-tuned checkpoint weights are subject to the non-commercial, research-only restriction above. The included SAM License and the licenses of the upstream SAM3 source, base weights, and dependencies also apply. Use is permitted only when all applicable terms are satisfied.
Citation
Please cite the ADOPD 2026 and ADOPD 2024 papers.
@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}
}
@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}
}