The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector
Caixia Zhou, Yaping Huang, Mengyang Pu, Qingji Guan, Li Huang and Haibin Ling
CVPR 2023
The processed dataset is from LPCB, you can download the used matlab code and processed data from the Baidu disk, the code is 3tii. The complete processed BSDS training dataset can be downloaded from the Google disk.
BSDS with single scale: https://drive.google.com/file/d/1nv2_TZRyiQh5oU9TnGMzu313OrspD2l5/view?usp=sharing
The dataset is highly based on the LPCB, and the code is highly based on RCF_Pytorch_Updated and
segmentation_models.pytorch. Many thanks for their great work.
Please consider citing this project in your publications if it helps your research.
@article{zhou2023treasure,
title={The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector},
author={Zhou, Caixia and Huang, Yaping and Pu, Mengyang and Guan, Qingji and Huang, Li and Ling, Haibin},
journal={arXiv preprint arXiv:2303.11828},
year={2023}
}
@inproceedings{deng2018learning,
title={Learning to predict crisp boundaries},
author={Deng, Ruoxi and Shen, Chunhua and Liu, Shengjun and Wang, Huibing and Liu, Xinru},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
pages={562--578},
year={2018}
}