EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Longfei Liu ^*‡  Yongjie Hou ^*  Yang Li ^*  Qirui Wang ^*  Youyang Sha 
Yongjun Yu  Yinzhi Wang  Peizhe Ru  Xuanlong Yu^†  Xi Shen ^†

* Equal Contribution    ‡ Project Leader    † Corresponding Author

Intellindust AI Lab

---

🚀 Updates

• [2026-03-21] We have uploaded our models on 🤗 Hugging Face.
• [2026-03-19] Initial release of EdgeCrafter.

---

🤗 Hugging Face

We have uploaded our models on 🤗 Hugging Face! You can also access these models via hf_models.ipynb. Have a try!

---

📍 Reproducing the Results

• Detection & Instance Segmentation: Instructions
• Pose Estimation: Instructions

---

🏆 Model Zoo

COCO2017 Validation Results

Note: Latency is measured on an NVIDIA T4 GPU with batch size 1 under FP16 precision using TensorRT (v10.6).

Object Detection

Model	Size	AP50:95	#Params	GFLOPs	Latency (ms)	Config	Log	Checkpoint
ECDet-S	640	51.7	10	26	5.41	config	log	model
ECDet-M	640	54.3	18	53	7.98	config	log	model
ECDet-L	640	57.0	31	101	10.49	config	log	model
ECDet-X	640	57.9	49	151	12.70	config	log	model

Instance Segmentation

Model	Size	AP50:95	#Params	GFLOPs	Latency (ms)	Config	Log	Checkpoint
ECSeg-S	640	43.0	10	33	6.96	config	log	model
ECSeg-M	640	45.2	20	64	9.85	config	log	model
ECSeg-L	640	47.1	34	111	12.56	config	log	model
ECSeg-X	640	48.4	50	168	14.96	config	log	model

Pose Estimation

Model	Size	AP50:95	#Params	GFLOPs	Latency (ms)	Config	Log	Checkpoint
ECPose-S	640	68.9	10	30	5.54	config	log	model
ECPose-M	640	72.4	20	63	9.25	config	log	model
ECPose-L	640	73.5	34	112	11.83	config	log	model
ECPose-X	640	74.8	51	172	14.31	config	log	model

---

📦 Installation

# Clone the repository
git clone https://github.com/your-org/edgecrafter.git
cd edgecrafter

# Create conda environment
conda create -n ec python=3.11 -y
conda activate ec

# Install dependencies
pip install -r requirements.txt

⚡ Quick Start (Inference)

The easiest way to test EdgeCrafter is to run inference on a sample image using a pre-trained model.

# 1. Download a pre-trained model (e.g., ECDet-L)
cd ecdetseg
wget https://github.com/capsule2077/edgecrafter/releases/download/edgecrafterv1/ecdet_l.pth
# 2. Run PyTorch inference
# Make sure to replace `path/to/your/image.jpg` with an actual image path
python tools/inference/torch_inf.py -c configs/ecdet/ecdet_l.yml -r ecdet_l.pth -i path/to/your/image.jpg

📄 License

This project is released under the Apache 2.0 License.

---

🙏 Acknowledgements

We thank the authors of the following open-source projects that made this work possible: RT-DETR, D-FINE, DEIM, lightly-train, DETRPose, RF-DETR, DINOv3

---

📚 Citation

If you find this project useful in your research, please consider citing:

@article{liu2026edgecrafter,
  title={EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation},
  author={Liu, Longfei and Hou, Yongjie and Li, Yang and Wang, Qirui and Sha, Youyang and Yu, Yongjun and Wang, Yinzhi and Ru, Peizhe and Yu, Xuanlong and Shen, Xi},
  journal={arXiv},
  year={2026}
}