Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection

The PyTorch code for ACM MM2021 paper “Complementary Trilateral Decoder for Fast and Accurate Salient Object Detection”

• Python 3.6
• Pytorch 1.4+
• OpenCV 4.0
• Numpy
• TensorboardX
• Apex

Download the SOD datasets and unzip them into data folder.

• We implement our method by PyTorch and conduct experiments on a NVIDIA 1080Ti GPU.
• We adopt pre-trained ResNet-18 and ResNet-50 as backbone networks, which are saved in res folder.
• We train our method on DUTS-TR and test our method on other datasets.
• After training, the trained models will be saved in out folder.

• After testing, saliency maps will be saved in eval folder.

• We use MATLAB code to evaluate the performace of our method.

This project is based on the implementation of F3Net.

GitHub

 

To finish reading, please visit source site