🚀 Rethinking Multi-Scale Representation Learning for Real-Time Object Detection
⭐ IEEE TPAMI 2025

📄 Table of Contents | ✨ Page | ⚔️ MMYOLO | 🎻 Ultralytics | 📖 Citation | 📜 License | ❓ FAQ

This repository contains the official implementation of the following paper:

YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection
Yuming Chen, Xinbin Yuan, Ruiqi Wu, Jiabao Wang, Qibin Hou, Ming-Ming Cheng
IEEE TPAMI 2025

Note: We provide two versions of YOLO-MS in this repository: one is based on MMYOLO, maintained by OpenMMLab, and the other is based on Ultraytics (will release soon).

• 📄 Table of Contents
• ✨ News 🔝
• ⚔️ MM-YOLO version 🔝
• 🎻 Ultralytics version 🔝
• 🏡 Model Zoo 🔝
• 🏗️ Supported Tasks 🔝
• 📖 Citation 🔝
• 📜 License 🔝
• 📮 Contact 🔝
• 🤝 Acknowledgement 🔝

Future work can be found in todo.md.

• Jun, 2025: ⭐ The new code is publicly available! The MMYOLO version is released.
• Feb, 2025: 🔥 Our code is also implemented based on Jittor, and avaliable at nk-yolo!
• Feb, 2025: 🔥 Our work is recipient of the “2024 Outstanding Technical Cooperation Project” award from Huawei!
• Jan, 2025: ⭐ Our paper is accepted by TPAMI!
• Dec, 2024: 🔥 Our work is applied in “Feng Chi Shan Pai” system of Huawei Mate 70 and P70!
• Aug, 2023: ⭐ Our code is publicly available!

If you find our repo useful for your research, please cite us:

@article{Chen2025,
  title = {YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection},
  ISSN = {1939-3539},
  url = {http://dx.doi.org/10.1109/TPAMI.2025.3538473},
  DOI = {10.1109/tpami.2025.3538473},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  author = {Chen, Yuming and Yuan, Xinbin and Wang, Jiabao and Wu, Ruiqi and Li, Xiang and Hou, Qibin and Cheng, Ming-Ming},
  year = {2025},
  pages = {1–14}
}

This project is based on the open source codebase MMYOLO.

@misc{mmyolo2022,
    title={{MMYOLO: OpenMMLab YOLO} series toolbox and benchmark},
    author={MMYOLO Contributors},
    howpublished = {\url{https://github.com/open-mmlab/mmyolo}},
    year={2022}
}

Licensed under a Creative Commons Attribution-NonCommercial 4.0 International for Non-commercial use only. Any commercial use should get formal permission first.

For technical questions, please contact chenyuming[AT]mail.nankai.edu.cn. For commercial licensing, please contact cmm[AT]nankai.edu.cn and andrewhoux[AT]gmail.com.

This repo is modified from open source real-time object detection codebase MMYOLO and Ultralytics.

The README file is referred to LED and CrossKD.