---
license: apache-2.0
---
# [NeurIPS 2023] Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation

This is the Hugging Face model repository for the paper "Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation," accepted by NeurIPS 2023.
📝 [Paper](https://proceedings.neurips.cc/paper_files/paper/2023/hash/708e0d691a22212e1e373dc8779cbe53-Abstract-Conference.html)
🐙 [GitHub](https://github.com/jinpeng0528/STAR)

## Installation & Data Preparation

Please follow the instructions provided in our [GitHub repository](https://github.com/jinpeng0528/STAR) for installation and data preparation.

## Evaluation

#### PASCAL VOC 2012
To evaluate on the PASCAL VOC 2012 dataset, execute the following command:

```shell
python eval_voc.py --device 0 --test --resume path/to/weight.pth
```

#### ADE20K
To evaluate on the ADE20K dataset, execute the following command:

```shell
python eval_ade.py --device 0 --test --resume path/to/weight.pth
```

## Citation

```
@inproceedings{chen2023saving,
  title={Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation},
  author={Chen, Jinpeng and Cong, Runmin and Luo, Yuxuan and Ip, Horace Ho Shing and Kwong, Sam},
  booktitle={NeurIPS},
  year={2023}
}
```