DiffusionDet: Diffusion Model for Object Detection
DiffusionDet is the first work of diffusion model for object detection.
DiffusionDet: Diffusion Model for Object Detection
Shoufa Chen, Peize Sun, Yibing Song, Ping Luo
arXiv 2211.09788
Updates
- (11/2022) Code is released.
Models
| Method | Box AP (1 step) | Box AP (4 step) | Download |
|---|---|---|---|
| COCO-Res50 | 45.5 | 46.1 | model |
| COCO-Res101 | 46.6 | 46.9 | model |
| COCO-SwinBase | 52.3 | 52.7 | model |
| LVIS-Res50 | 30.4 | 31.8 | model |
| LVIS-Res101 | 31.9 | 32.9 | model |
| LVIS-SwinBase | 40.6 | 41.9 | model |
Getting Started
The installation instruction and usage are in Getting Started with DiffusionDet.
License
This project is under the CC-BY-NC 4.0 license. See LICENSE for details.
Citing DiffusionDet
If you use DiffusionDet in your research or wish to refer to the baseline results published here, please use the following BibTeX entry.
@article{chen2022diffusiondet,
title={DiffusionDet: Diffusion Model for Object Detection},
author={Chen, Shoufa and Sun, Peize and Song, Yibing and Luo, Ping},
journal={arXiv preprint arXiv:2211.09788},
year={2022}
}