1.BIDP

This is BIDP: Brain-Inspired Dual-Process CNN-Transformer for Salient Object Detection official code

2.architecture

3.result

4.Evaluation

For PR curve and F curve, we use the code provided by this repo: [BASNet, CVPR-2019] For MAE, F measure, E score and S score, we use the code provided by this repo: [F3Net, AAAI-2020] code

5.Quantitative comparisons

6.Requirements

python==3.8

torch==2.0

Torchvision

Numpy

7.Dataset

For all datasets, they should be organized in below's fashion:

|__dataset_name

   |__Images: xxx.jpg ...
   
   |__Masks : xxx.png ...

download dataset ECSSD HKU-IS DUTS-TE DUT-OMRON PASCAL-S

8.Train

pyton main.py