Awesome
Online Confidence Estimation - OCENet
<!-- <p align="center"><img src="introduction_figure.png" alt="introduction_figure" width="90%"></p> -->The implementation of Modeling Aleatoric Uncertainty for Camouflaged Object Detection, Jiawei Liu, Jing Zhang and Nick Barnes, [Paper].
Citation
If you find the code useful, please consider citing our paper using the following BibTeX entry.
@InProceedings{Liu_2022_WACV,
author = {Liu, Jiawei and Zhang, Jing and Barnes, Nick},
title = {Modeling Aleatoric Uncertainty for Camouflaged Object Detection},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {January},
year = {2022},
pages = {1445-1454}
}
Requirements
- Python 3.6
- pytorch 1.3.0, torchvision 0.4.1
- CUDA 10.1
- 2 x 2080Ti GPU
Download COD10K training set through Google Drive link or Baidu Pan link with the fetch code:djq2.
Usage
- Training
CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 --master_port=3000 train.py
- Inference
Download the weight of CODNet and OCENet from the [Google Drive]
CUDA_VISIBLE_DEVICES=0 python test.py
- Evaluation
Please use the SOD evaluation toolbox provided by jiwei0921.
Results
The prediction results can be downloaded from [Google Drive]