|
|
--- |
|
|
license: apache-2.0 |
|
|
pipeline_tag: image-segmentation |
|
|
library_name: pytorch |
|
|
--- |
|
|
|
|
|
# [ECCV 2024] Strike a Balance in Continual Panoptic Segmentation |
|
|
|
|
|
This is the Hugging Face model repository for the paper "Strike a Balance in Continual Panoptic Segmentation", accepted by ECCV 2024. |
|
|
📝 [Paper](https://arxiv.org/abs/2407.16354) |
|
|
🐙 [GitHub](https://github.com/jinpeng0528/BalConpas) |
|
|
|
|
|
## Installation & Data Preparation |
|
|
|
|
|
Please follow the instructions provided in our [GitHub repository](https://github.com/jinpeng0528/BalConpas) for installation and data preparation. |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
To evaluate the trained model, add the arguments `--eval-only --resume` to the command line. For example: |
|
|
|
|
|
```bash |
|
|
python train_continual.py --eval-only --resume --config-file configs/ade20k/panoptic-segmentation/100-10.yaml \ |
|
|
CONT.TASK 6 OUTPUT_DIR ./output/ps/100-10/step6 |
|
|
``` |
|
|
|
|
|
## Citation |
|
|
|
|
|
``` |
|
|
@inproceedings{chen2024strike, |
|
|
title={Strike a Balance in Continual Panoptic Segmentation}, |
|
|
author={Chen, Jinpeng and Cong, Runmin and Luo, Yuxuan and Ip, Horace Ho Shing and Kwong, Sam}, |
|
|
booktitle={ECCV}, |
|
|
year={2024} |
|
|
} |
|
|
``` |
|
|
|
|
|
|
|
|
|
|
|
|
