Skip to content

The implementation of 'M3Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection'.

License

Notifications You must be signed in to change notification settings

I2-Multimedia-Lab/M3Net

 
 

Repository files navigation

M3Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection

PWC PWC PWC PWC PWC

Source code of 'M3Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection'. paper link

Environment

Python 3.9.13 and Pytorch 1.11.0. Details can be found in requirements.txt.

Data Preparation

All datasets used can be downloaded at here [arrr].

Training set

We use the training set of DUTS to train our M3Net.

Testing Set

We use the testing set of DUTS, ECSSD, HKU-IS, PASCAL-S, DUT-O, and SOD to test our M3Net. After Downloading, put them into /datasets folder.

Your /datasets folder should look like this:

-- datasets
   |-- DUT-O
   |   |--imgs
   |   |--gt
   |-- DUTS-TR
   |   |--imgs
   |   |--gt
   |-- ECSSD
   |   |--imgs
   |   |--gt
   ...

Training and Testing

  1. Download the pretrained backbone weights and put it into pretrained_model/ folder. ResNet [uxcz], SwinTransformer, T2T-ViT, EfficientNet are currently supported.

  2. Run python train_test.py --train True --test True --record='record.txt' for training and testing. The predictions will be in preds/ folder and the training records will be in record.txt file.

Evaluation

Pre-calculated saliency maps: M3Net-R [uqsr], M3Net-S [6jyh]
Pre-trained weights: M3Net-R [m789], M3Net-S [4wnw]

For PR curve and F curve, we use the code provided by this repo: [BASNet, CVPR-2019].
For MAE, Weighted F measure, E score and S score, we use the code provided by this repo: [PySODMetrics].

For more information about evaluation, please refer to Evaluation/Guidance.md.

Evaluation Results

Quantitative Evaluation

Precision-recall and F-measure curves

Visual Comparison

Acknowledgement

Our idea is inspired by VST and MiNet. Thanks for their excellent works. We also appreciate the data loading and enhancement code provided by plemeri, as well as the efficient evaluation tool provided by lartpang.

Citation

If you think our work is helpful, please cite

@misc{yuan2023m3net,
      title={M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection}, 
      author={Yao Yuan and Pan Gao and XiaoYang Tan},
      year={2023},
      eprint={2309.08365},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

About

The implementation of 'M3Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection'.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 64.7%
  • Python 35.3%