This project provides the code and results for 'LSNet: Lightweight Spatial Boosting Network for Detecting Salient Objects in RGB-Thermal Images', IEEE TIP, 2023. IEEE link
Python 3.7+, Pytorch 1.5.0+, Cuda 10.2+, TensorboardX 2.1, opencv-python
If anything goes wrong with the environment, please check requirements.txt for details.
- Download the RGB-T raw data from baidu, pin: sf9y / Google drive
- Download the RGB-D raw data from baidu, pin: 7pi5 / Google drive
Note that the depth maps of the raw data above are foreground is white.
modify the train_root train_root save_path path in config.py according to your own data path.
-
Train the LSNet:
python train.py
modify the test_path path in config.py according to your own data path.
-
Test the LSNet:
python test.py
Note that task in config.py determines which task and dataset to use.
- You can select one of toolboxes to get the metrics CODToolbox / PySODMetrics
- RGB-T baidu pin: fxsk / Google drive
- RGB-D baidu pin: 6352 / Google drive
Note that we resize the testing data to the size of 224 * 224 for quicky evaluate.
please check our previous works APNet and CCAFNet.
- RGB-T baidu pin: wnoa / Google drive
- RGB-D baidu pin: wnoa / Google drive
@ARTICLE{Zhou_2023_LSNet,
author={Zhou, Wujie and Zhu, Yun and Lei, Jingsheng and Yang, Rongwang and Yu, Lu},
journal={IEEE Transactions on Image Processing},
title={LSNet: Lightweight Spatial Boosting Network for Detecting Salient Objects in RGB-Thermal Images},
year={2023},
volume={32},
number={},
pages={1329-1340},
doi={10.1109/TIP.2023.3242775}}
The implement of this project is based on the codebases bellow.
- BBS-Net
- Knowledge-Distillation-Zoo
- Fps/speed test MobileSal
- Evaluate tools CODToolbox / PySODMetrics
If you find this project helpful, Please also cite codebases above.
Please drop me an email for any problems or discussion: https://wujiezhou.github.io/ ([email protected]) or [email protected].