[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. ๐ Paper ๐ GitHub
Installation & Data Preparation
Please follow the instructions provided in our GitHub repository for installation and data preparation.
Evaluation
To evaluate the trained model, add the arguments --eval-only --resume
to the command line. For example:
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}
}
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The HF Inference API does not support image-segmentation models for pytorch library.