DiffusionInst is the first work of diffusion model for instance segmentation.
We hope our work could serve as a simple yet effective baseline, which could inspire designing more efficient diffusion frameworks for challenging discriminative tasks.
DiffusionInst: Diffusion Model for Instance Segmentation
Zhangxuan Gu, Haoxing Chen, Zhuoer Xu, Jun Lan, Changhua Meng, Weiqiang Wang arXiv 2212.02773
- Release source code.
- Adding directly filter denoising.
The installation instruction and usage are in Getting Started with DiffusionInst.
| Method | Mask AP (1 step) | Mask AP (4 step) |
|---|---|---|
| COCO-Res50 | 35.1 | 35.5 |
| COCO-Res101 | 36.3 | 36.5 |
| COCO-Swin-B | 44.0 | 44.2 |
| LVIS-Res50 | 22.3 | - |
| LVIS-Res101 | 24.6 | - |
| LVIS-Swin-B | 34.8 | - |
If you use DiffusionInst in your research or wish to refer to the baseline results published here, please use the following BibTeX entry.
@article{DiffusionInst,
title={DiffusionInst: Diffusion Model for Instance Segmentation},
author={Gu, Zhangxuan and Chen, Haoxing and Xu, Zhuoer and Lan, Jun and Meng, Changhua and Wang, Weiqiang},
journal={arXiv preprint arXiv:2212.02773},
year={2022}
}Many thanks to the nice work of DiffusionDet @ShoufaChen. Our codes and configs follow DiffusionDet.
Please feel free to contact us if you have any problems.
Email: haoxingchen@smail.nju.edu.cn or guzhangxuan.gzx@antgroup.com