Official Implementation of ACM-MM 2023 paper "Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation"

Jialun Pei, Zhangjun Zhou, Yueming Jin, He Tang✉, and Pheng-Ann Heng

[Paper]; [Official Version]

Contact: [email protected], [email protected]

• Linux with python ≥ 3.8
• Pytorch ≥ 1.7 and torchvison that matches the Pytorch installation.
• Opencv
• Numpy
• Apex

• DIS5K

1. Download the datasets and put them in the same folder. To match the folder name in the dataset mappers, you'd better not change the folder names, its structure may be:

    DATASET_ROOT/
    ├── DIS5K
       ├── DIS-TR
          ├── im
          ├── gt
          ├── trunk-origin
          ├── struct-origin
       ├── DIS-VD
          ├── im
          ├── gt
       ├── DIS-TE1
          ├── im
          ├── gt
       ├── DIS-TE2
          ├── im
          ├── gt
       ├── DIS-TE3
          ├── im
          ├── gt
       ├── DIS-TE4
          ├── im
          ├── gt

• Download the pre-training weights into UDUN-master/pre .

Download the optimized model weights and store them in UDUN-master/model.

The visual results of our UDUN with ResNet-50 trained on Overall DIS-TE.

• Results on the Overall DIS-TE test set: Quark/ Google

The visual results of other SOTAs on Overall DIS-TE.

• Results on the Overall DIS-TE test set: Quark/ Google

• To train our UDUN on single GPU by following command,the trained models will be saved in savePath folder. You can modify datapath if you want to run your own datases.

./train.sh

• To test our UDUN on DIS5K, the prediction maps will be saved in DIS5K_Pre folder.

python3 test.py 

• To Evaluate the predicted results.

cd metrics
python3 test_metrics.py 
python3 hce_metric_main.py

• Split the ground truth into trunk map and struct map, which will be saved into DIS5K-TR/gt/Trunk-origin and DIS5K-TR/gt/struct-origin.

cd utils
python3 utils.py

This work is based on:

• LDF

Thanks for their great work!

If this helps you, please cite this work:

@inproceedings{pei2023unite,
  title={Unite-Divide-Unite: Joint Boosting Trunk and Structure for High-accuracy Dichotomous Image Segmentation},
  author={Pei, Jialun and Zhou, Zhangjun and Jin, Yueming and Tang, He and Pheng-Ann, Heng},
  booktitle={Proceedings of the 31st ACM International Conference on Multimedia},
  pages={2139--2147},
  year={2023},
}