2025.1 our paper has been accepted by IEEE TIP link.
2024.2 arxiv paper released.
Building upon this work, we further proposed JoNet to investigate the joint learning of the two tasks. If you're interested, you can find the paper here.
you can find them here.
you can download here.
During development, we referred to the following resources:
- MAE - The backbone of SENet is built based on this project. Note that to get good results, you need to use the full pre-trained weights of MAE (including the decoder part). you can get the mae weight here.
- BGNet - The training process and implementation are based on this project.
if you think our work is helpful, please cite
@article{hao2025simple,
title={A simple yet effective network based on vision transformer for camouflaged object and salient object detection},
author={Hao, Chao and Yu, Zitong and Liu, Xin and Xu, Jun and Yue, Huanjing and Yang, Jingyu},
journal={IEEE Transactions on Image Processing},
year={2025},
publisher={IEEE}
}