Home

Awesome

BgNet

Boundary-guided Network for Camouflaged Object Detection

This repo. is an official implementation of the BgNet , which has been accepted in the journal Knowledge-based systems, 2022.

The main pipeline is shown as the following, BgNet

And some results are presented quantitative results qualitative results

Dependencies

>= Pytorch 1.0.0
OpenCV-Python
[optional] matlab

Datasets

Training and testing datasets are available at

(Baidu) [code:q5e4]

(Google)

Training

python train.py

Test

 python test.py

We provide the trained model file (Baidu Res2Net) [code:1fau] (Baidu ResNet) [code:lzzo]

(Google Res2Net) (Google ResNet)

The prediction maps are also available (Res2Net)[code:rbxb] (ResNet)[code:uajy]

Citation

Please cite the BgNet in your publications if it helps your research:

@article{CHEN2022,
  title = {Boundary-guided Network for Camouflaged Object Detection},
  author = {Tianyou Chen and Jin Xiao and Xiaoguang Hu and Guofeng Zhang and Shaojie Wang},
  journal = {Knowledge-Based Systems},
  year = {2022},
}

Reference

BBSNet CPD