This repository includes the trained model, code and results for our paper:

Boundary-guided muti-scale refinement network for camouflaged object detection. The Visual Computer

Pre-Trained Model

The pre-trained model can be found on https://pan.baidu.com/s/1HGS1PZBrhe25B7KS3fLIaQ (code: s7bs)

Dataset

The testing dataset (COD10K-test + CAMO-test + CHAMELEON) and move it into ./Dataset/TestDataset/, which can be found on https://drive.google.com/file/d/1QEGnP9O7HbN_2tH999O3HRIsErIVYalx/view?usp=sharing.

The training dataset (COD10K-train) which can be found on https://drive.google.com/file/d/1D9bf1KeeCJsxxri6d2qAC7z6O1X_fxpt/view?usp=sharing.

Trained Model

The trained model can be found on: https://pan.baidu.com/s/1xksNTW6Y4WiaB_FlvTrzLg (code: ztnf)

Results

The result maps can be found on: https://pan.baidu.com/s/1UDg_doRufKh4_oySPUowMg (code: bgmr)

Evaluation

Matlab version: https://github.com/DengPingFan/CODToolbox

Python version: https://github.com/lartpang/PySODEvalToolkit

Contact

If you have any questions, feel free to E-mail me via: hhu_yeqian@hhu.edu.cn