Authors: Ruozhen He*, Qihua Dong*, Jiaying Lin, and Rynson Lau (* joint first authors)
Paper Link: arxiv
- We relabeled 4,040 images (3,040 from COD10K, 1,000 from CAMO) with scribbles and proposed the S-COD dataset (Download) for training. In our annotations, "1" stands for foregrounds, "2" for backgrounds, and "0" for unlabeled regions. (The image is viewed as black because its range is 0-255)
- Download the training dataset (COD10K-train) at here.
- Download the testing dataset (COD10K-test + CAMO-test + CHAMELEON) at here.
- We provide CRNet testing maps and training weights presented in the papers.
git clone --recurse-submodules https://github.com/dddraxxx/Weakly-Supervised-Camouflaged-Object-Detection-with-Scribble-Annotations.git
pip install -r requirements.txt
The pretrained weight can be found here: ResNet-50.
- Download the dataset and pretrained model. (examples of
train.txt
andtest.txt
are in the path./CodDataset
) - Modify the path in
train.py
. - Run
python train.py
.
- The evaluation is done using the submodule PySODEvalToolKit. Add the json files according to its instruction. (examples of json files are in the path
./CodDataset
) - Modify the path and filename.
- Run
python test.py
.
The code is partly based on SCWSSOD, GCPANet and GatedCRFLoss.