Home

Awesome

MFNet

Source code for "MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection", accepted in ICCV-2021. The paper's PDF can be found in Here.

Yongri Piao, Jian Wang (co-first), Miao Zhang and Huchuan Lu. IIAU-OIP Lab.

image

Prerequisites

environment

training data

link: https://pan.baidu.com/s/1omTCChQFWwNFhQ79AVD8rg. code: oipw

testing datasets

link: https://pan.baidu.com/s/1PBzDP1Hnf3RIvpARmxn2yA. code: oipw

Training

1st training stage

Case1: Please refer to this repository.

Case2: We also upload ready-made pseudo labels in Training data (the link above), you can directly use our offered two kinds of pseudo labels for convenience. CAMs are also presented if you needed.

2nd training stage

1, setting the training data to the proper root as follows:

MF_code -- data -- DUTS-Train -- image -- 10553 samples

                -- ECSSD (not necessary) 
                
                -- pseudo labels -- label0_0 -- 10553 pseudo labels
                
                                 -- label1_0 -- 10553 pseudo labels

2, training

Run main.py

Here you can set ECCSD dataset as validation set for optimal results by setting --val to True, of course it is not necessary in our work.

Testing

Run test_code.py

You need to configure your desired testset in --test_root. Here you can also perform PAMR and CRF on saliency maps for a furthur refinements if you want, by setting --pamr and --crf to True. Noting that the results in our paper do not adopt these post-process for a fair comparison.

The evaluation code can be found in here.

Saliency maps & Checkpoint

We offer our saliency maps and checkpoints on various backbones (including DenseNet-169, ResNet-101, ResNet-50 and VGG-16) for more convenient comparison in the future. The results in our paper are all come from the model based on DenseNet-169, and we also highly recommend the following researchers adopt same backbone for a more fair and convenient comparison.

Saliency maps

link: https://pan.baidu.com/s/1IRTEaEicYaCJ2TYjZV1lZA. code: oipw

Checkpoints

link: https://pan.baidu.com/s/14sLu8BtdthD0e8SPK1CT3w. code: oipw

Contact me

If you have any questions, please contact me: [jiangnanyimi@163.com].

Acknowledge

Thanks to pioneering helpful works:

Citation

We really hope this repo can contribute the conmunity, and if you find this work useful, please use the following citation:

@InProceedings{Piao_2021_ICCV,
    author    = {Piao, Yongri and Wang, Jian and Zhang, Miao and Lu, Huchuan},
    title     = {MFNet: Multi-Filter Directive Network for Weakly Supervised Salient Object Detection},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {4136-4145}
}