Yoloe V8s Seg

🚀 YOLOE: Real-Time Zero-Shot Object Detection

YOLOE is a real-time zero-shot object detection model, offering efficient and accurate object detection capabilities.

🚀 Quick Start

This model can be used for zero-shot object detection. For detailed usage, please refer to the sections below.

✨ Features

• Pipeline tag: zero-shot-object-detection
• Tags: model_hub_mixin, pytorch_model_hub_mixin

📦 Installation

pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/CLIP
pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/ml-mobileclip
pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/lvis-api
pip install git+https://github.com/THU-MIG/yoloe.git

wget https://docs-assets.developer.apple.com/ml-research/datasets/mobileclip/mobileclip_blt.pt

📚 Documentation

Model Description

YOLOE: Real-Time Seeing Anything

• arXiv: https://arxiv.org/abs/2503.07465
• github: https://github.com/THU-MIG/yoloe

Prediction

Please refer to Prediction Section.

Transferring

Please refer to Transferring Section.

Validation

Please refer to Validation Section.

Training

Please refer to Training Section.

BibTeX Entry and Citation Info

@misc{wang2025yoloerealtimeseeing,
      title={YOLOE: Real-Time Seeing Anything}, 
      author={Ao Wang and Lihao Liu and Hui Chen and Zijia Lin and Jungong Han and Guiguang Ding},
      year={2025},
      eprint={2503.07465},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.07465}, 
}

📄 License

This project is licensed under the AGPL-3.0 license.