ajunlonglive / detrex

detrex is a research platform for Transformer-based Object Detection algorithms including DETR (ECCV 2020), Deformable-DETR (ICLR 2021), Conditional-DETR (ICCV 2021), DAB-DETR (ICLR 2022), DN-DETR (CVPR 2022), DINO (arXiv 2022), H-DETR (arXiv 2022), MaskDINO (arXiv 2022), etc.

detrex

📘Documentation | 🛠️Installation | 👀Model Zoo | 🚀Awesome DETR | 🆕News | 🤔Reporting Issues

Introduction

detrex is an open-source toolbox that provides state-of-the-art Transformer-based detection algorithms. It is built on top of Detectron2 and its module design is partially borrowed from MMDetection and DETR. Many thanks for their nicely organized code. The main branch works with Pytorch 1.10+ or higher (we recommend Pytorch 1.12).

Major Features

• Modular Design. detrex decomposes the Transformer-based detection framework into various components which help users easily build their own customized models.

• State-of-the-art Methods. detrex provides a series of Transformer-based detection algorithms, including DINO which reached the SOTA of DETR-like models with 63.3AP!

• Easy to Use. detrex is designed to be light-weight and easy for users to use:

  • LazyConfig System for more flexible syntax and cleaner config files.
  • Light-weight training engine modified from detectron2 lazyconfig_train_net.py

Apart from detrex, we also released a repo Awesome Detection Transformer to present papers about Transformer for detection and segmentation.

Fun Facts

The repo name detrex has several interpretations:

• detr-ex : We take our hats off to DETR and regard this repo as an extension of Transformer-based detection algorithms.

• det-rex : rex literally means 'king' in Latin. We hope this repo can help advance the state of the art on object detection by providing the best Transformer-based detection algorithms from the research community.

• de-t.rex : de means 'the' in Dutch. T.rex, also called Tyrannosaurus Rex, means 'king of the tyrant lizards' and connects to our research work 'DINO', which is short for Dinosaur.

What's New

v0.2.0 was released on 13/11/2022:

• Release new baselines for DINO-R50-12ep, DINO-Swin-Large-36ep, DAB-Deformable-DETR-R50-50ep, DAB-Deformable-DETR-R50-Two-Stage, please check Model Zoo.
• Rebuild more clear config files for projects.
• Support H-Deformable-DETR
• Release H-Deformable-DETR pretrained weights including H-Deformable-DETR-R50, H-Deformable-DETR-Swin-Tiny, H-Deformable-DETR-Swin-Large in H-Deformable-DETR
• Add demo for visualizing customized input images or videos using pretrained weights in demo

Please see changelog.md for details and release history.

Installation

Please refer to Installation Instructions for the details of installation.

Getting Started

Please refer to Getting Started with detrex for the basic usage of detrex. We also provides other tutorials for:

• Learn about the config system of detrex
• How to convert the pretrained weights from original detr repo into detrex format
• Visualize your training data and testing results on COCO dataset
• Analyze the model under detrex
• Download and initialize with the pretrained backbone weights
• Frequently asked questions

Documentation

Please see documentation for full API documentation and tutorials.

Model Zoo

Results and models are available in model zoo.

Supported methods

• DETR (ECCV'2020)
• Deformable-DETR (ICLR'2021 Oral)
• Conditional-DETR (ICCV'2021)
• DAB-DETR (ICLR'2022)
• DAB-Deformable-DETR (ICLR'2022)
• DN-DETR (CVPR'2022 Oral)
• DN-Deformable-DETR (CVPR'2022 Oral)
• DINO (ArXiv'2022)
• Group-DETR (ArXiv' 2022)
• H-Deformable-DETR (ArXiv' 2022)

Please see projects for the details about projects that are built based on detrex.

License

This project is released under the Apache 2.0 license.

Acknowledgement

• detrex is an open-source toolbox for Transformer-based detection algorithms created by researchers of IDEACVR. We appreciate all contributions to detrex!
• detrex is built based on Detectron2 and part of its module design is borrowed from MMDetection, DETR, and Deformable-DETR.

Citation

If you find the projects held by detrex useful in your research, please consider cite:

Citation List

• Cite detrex

@misc{ideacvr2022detrex,
  author =       {detrex contributors},
  title =        {detrex: An Research Platform for Transformer-based Object Detection Algorithms},
  howpublished = {\url{https://github.com/IDEA-Research/detrex}},
  year =         {2022}
}

• Cite DETR

@inproceedings{carion2020end,
  title={End-to-end object detection with transformers},
  author={Carion, Nicolas and Massa, Francisco and Synnaeve, Gabriel and Usunier, Nicolas and Kirillov, Alexander and Zagoruyko, Sergey},
  booktitle={European conference on computer vision},
  pages={213--229},
  year={2020},
  organization={Springer}
}

• Cite Deformable-DETR

@article{zhu2020deformable,
  title={Deformable DETR: Deformable Transformers for End-to-End Object Detection},
  author={Zhu, Xizhou and Su, Weijie and Lu, Lewei and Li, Bin and Wang, Xiaogang and Dai, Jifeng},
  journal={arXiv preprint arXiv:2010.04159},
  year={2020}
}

• Cite Conditional-DETR

@inproceedings{meng2021-CondDETR,
  title       = {Conditional DETR for Fast Training Convergence},
  author      = {Meng, Depu and Chen, Xiaokang and Fan, Zejia and Zeng, Gang and Li, Houqiang and Yuan, Yuhui and Sun, Lei and Wang, Jingdong},
  booktitle   = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
  year        = {2021}
}

• Cite DAB-DETR

@inproceedings{
      liu2022dabdetr,
      title={{DAB}-{DETR}: Dynamic Anchor Boxes are Better Queries for {DETR}},
      author={Shilong Liu and Feng Li and Hao Zhang and Xiao Yang and Xianbiao Qi and Hang Su and Jun Zhu and Lei Zhang},
      booktitle={International Conference on Learning Representations},
      year={2022},
      url={https://openreview.net/forum?id=oMI9PjOb9Jl}
}

• Cite DN-DETR

@inproceedings{li2022dn,
      title={Dn-detr: Accelerate detr training by introducing query denoising},
      author={Li, Feng and Zhang, Hao and Liu, Shilong and Guo, Jian and Ni, Lionel M and Zhang, Lei},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      pages={13619--13627},
      year={2022}
}

• Cite DINO

@misc{zhang2022dino,
      title={DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection}, 
      author={Hao Zhang and Feng Li and Shilong Liu and Lei Zhang and Hang Su and Jun Zhu and Lionel M. Ni and Heung-Yeung Shum},
      year={2022},
      eprint={2203.03605},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

• Cite Group-DETR

@article{chen2022group,
  title={Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment},
  author={Chen, Qiang and Chen, Xiaokang and Wang, Jian and Feng, Haocheng and Han, Junyu and Ding, Errui and Zeng, Gang and Wang, Jingdong},
  journal={arXiv preprint arXiv:2207.13085},
  year={2022}
}

• Cite H-DETR

@article{jia2022detrs,
  title={DETRs with Hybrid Matching},
  author={Jia, Ding and Yuan, Yuhui and He, Haodi and Wu, Xiaopei and Yu, Haojun and Lin, Weihong and Sun, Lei and Zhang, Chao and Hu, Han},
  journal={arXiv preprint arXiv:2207.13080},
  year={2022}
}