---
title: BARM
canonical_url: "https://www.modelscope.cn/models/UltraDoughnut/BARM"
md_url: "https://www.modelscope.cn/models/UltraDoughnut/BARM.md"
repository: UltraDoughnut/BARM
last_updated: 2024-07-04
pipeline_tag: semantic-segmentation
tasks:
  - semantic-segmentation
library_name:
  - pytorch
frameworks:
  - Pytorch
downloads: 31
stars: 0
---

# BARM

> BARM - UltraDoughnut 在 ModelScope 开源的模型。BARM

- **Repository**: UltraDoughnut/BARM
- **Tasks**: semantic-segmentation
- **Downloads**: 31
- **Stars**: 0
- **Last updated**: 2024-07-04

Source: https://www.modelscope.cn/models/UltraDoughnut/BARM

---

# BARM - Official Trained Weights (ECCV 2024)

**Background Adaptation with Residual Modeling for Exemplar-Free
Class-Incremental Semantic Segmentation** <br />
Anqi Zhang<sup>1</sup>, Guangyu Gao<sup>1</sup>

<sup>1</sup> <sub>School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China</sub><br />

Accepted in ECCV 2024 <br />


## Download

The official weights of trained models for [BARM](https://github.com/ANDYZAQ/BARM). 

#### You can download the `.pth` files by using the SDK of modelscope, or simply use git. 

Download by SDK
```bash
# Install ModelScope
pip install modelscope
```
```python
# Download by SDK
from modelscope import snapshot_download
model_dir = snapshot_download('UltraDoughnut/BARM')
```
Download by Git
```bash
# Download by Git
git clone https://www.modelscope.cn/UltraDoughnut/BARM.git
```

## Citation
```
@inproceedings{zhang2024background,
  title={Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentation},
  author={Zhang, Anqi and Gao, Guangyu},
  journal={ECCV},
  year={2024}
}
```