PSOD (Point Saliency)

Weakly-Supervised Salient Object Detection Using Point Supervision

Prerequisites

Python 3.6
Pytorch 1.7
TensorboardX
OpenCV 3.4
Numpy 1.19

Clone repository

git clone git@github.com:shuyonggao/PSOD.git
cd PSOD

Download P-DUTS Dataset

point supervised DUTS: google
training images and "train.txt" file: google

Download Relevant Necessary Data

R50+ViT-B pretrained model: google
edge maps: google
gray image: google

Saliency map & Trained model

trained model: google
saliency maps: google
initial pseudo-labels: google

Train Model

Put the R50+ViT-B pretrained model into "models" folder.
Create the "dataset" folder in the main dirctory ("PSOD"). You should modify the create_link.sh file, then run it to create the soft link.

|----dataset
        |---edge
        |---gray
        |---image
        |---json
        |---train.txt
        |---filled_correct_img_gt  # Run "utills/EdgePoint2gt.py"
        |---filled_correct_mask  # Run "utills/EdgePoint2gt.py"

The Point supervison (json) and edge maps (edge) are employed to generate initial pseudo-labels (we provided the initial pseudo-labels and you can use it directly for training, or you can run python utils/EdgePoint2gt.py) to make initial pseudo-labels.

We organize all steps into a shell file, you can run bash edgepoint2gt_train_nss_retrain.sh to complete the entire training process.

Test Model

Set the path of the test data in test.py.
Create "out_2nd" folder and put the trained model into "out_2nd" folder.

Run python test.py

The saliency maps will be saved in the "eval/maps" folder.
We also provied the final saliency maps saliency maps: google.

Evaluation Code

The "Eval_SingleMeth_MulDataset.py" in "Saliency-Evaluation-numpy" folder is used to evaluate the saliency maps.

Citation

*If you find this work is helpful, please cite our paper:

@InProceedings{PSOD_aaai2022,
  title={Weakly-Supervised Salient Object Detection Using Point Supervision},
  author={Gao, Shuyong and Zhang, Wei and Wang, Yan and Guo, Qianyu and Zhang, Chenglong and He, Yangji and Zhang, Wenqiang},
  booktitle={AAAI},
  year={2022}
}

Acknowledgement

Weakly-Supervised Salient Object Detection via Scribble Annotations
Structure-Consistent Weakly Supervised Salient Object Detection with Local Saliency Coherence
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers

rejoicesyc/PSOD