EntitySeg is an open source toolbox which towards open-world and high-quality image segmentation. All works related to image segmentation from our group are open-sourced here.
To date, EntitySeg implements the following algorthms:
- Open-World Entity Segmentation (TAPMI2022) --- released
- High Quality Segmentation for Ultra High-resolution Images (CVPR2022) --- released
- CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation (ECCV2022) --- code to be released
- Fine-Grained Entity Segmentation --- paper, dataset and code to be released
- Automatically Discovering Novel Visual Categories with Adaptive Prototype Learning --- code to be released
Please refer to the README.md of each project. All projects would be merged to support each other in the soon.
@article{qi2021open,
title={Open-World Entity Segmentation},
author={Qi, Lu and Kuen, Jason and Wang, Yi and Gu, Jiuxiang and Zhao, Hengshuang and Lin, Zhe and Torr, Philip and Jia, Jiaya},
journal={arXiv preprint arXiv:2107.14228},
year={2021}
}
@article{shen2021high,
title={High Quality Segmentation for Ultra High-resolution Images},
author={Tiancheng Shen, Yuechen Zhang, Lu Qi, Jason Kuen, Xingyu Xie, Jianlong Wu, Zhe Lin, Jiaya Jia},
journal={CVPR},
year={2022}
}
@article{qi2022cassl,
title={CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation},
author={Qi, Lu and Kuen, Jason and Lin, Zhe and Gu, Jiuxiang and Rao, Fengyun and Li, Dian and Guo, Weidong and Wen, Zhen and Yang, Ming-Hsuan and Jia, Jiaya},
journal={ECCV},
year={2022}
}