clone repo:
git clone https://github.com/zengxianyu/jsws.git
git submodule init
git submodule update
prepare environment:
conda env create --file=environments.yaml
SegmentationClassAug (Onedrive)
train using image-level class labels and saliency ground-truth:
weak_seg_full_sal_train.pyOpen the file output/logs/train1.html in browser for visualization
It should be easy to achieve MIOU>54 but you may need to try multiple times to get the score MIOU 57.1 or more than that in Table. 5 of the paper.
train a more complex model using the prediction of the model trained in the stage 1.
syn_stage1.py
self_seg_full_sal_train.pydownload saliency maps (Google Drive); One Drive
@inproceedings{zeng2019joint,
title={Joint learning of saliency detection and weakly supervised semantic segmentation},
author={Zeng, Yu and Zhuge, Yunzhi and Lu, Huchuan and Zhang, Lihe},
booktitle={Proceedings of the IEEE International Conference on Computer Vision},
year={2019}
}