HUuxiaobin / HitNet

Camouflaged Object Detection

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

The more qualitative results of HitNet on four benchmarks (CAMO, CHAMELEON, NC4K, COD10K) have already been stored in Google Drive.

The pretrained model is stored in Google Drive. After downloading, please put it in the pretrained_pvt fold.

Our well-trained model is stored in Google Drive, which should be moved into the fold 'model_pth'.

run sh train.sh for training, test.sh for testing.

benchmark



@article{hu2022high,
  title={High-resolution Iterative Feedback Network for Camouflaged Object Detection},
  author={Hu, Xiaobin and  Wang,Shuo and Qin, Xuebin and Dai, Hang and Ren, Wenqi and Tai, Ying and Wang, Chengjie and Shao, Ling},
  journal={arXiv preprint arXiv:2203.11624},
  year={2022}
}

About

Camouflaged Object Detection


Languages

Language:Python 99.9%Language:Shell 0.1%