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
Download the SOD datasets and unzip them into
cd src python train.py
- 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
- We train our method on DUTS-TR and test our method on other datasets.
- After training, the trained models will be saved in
cd src python test.py
- After testing, saliency maps will be saved in
- CTDNet-18： saliency maps (提取码：b6ba)； trained model (提取码：ftmz）
- CTDNet-50： saliency maps (提取码：j1zq)； trained model (提取码：ehvv）
cd eval matlab main
- We use MATLAB code to evaluate the performace of our method.
This project is based on the implementation of F3Net.