Awesome

APNet

Code and result about APNet(IEEE TETCI)<br> 'APNet: Adversarial-Learning-Assistance and Perceived Importance Fusion Network for All-Day RGB-T Salient Object Detection'

Requirements

Python 3.7, Pytorch 1.5.0+, Cuda 10.2, TensorboardX 2.1, opencv-python

Dataset and Evaluate tools

RGB-T SOD Datasets can be found in: https://github.com/lz118/RGBT-Salient-Object-Detection <br>

Evaluate tools: we use the matlab verison provide by Dengping Fan.

Result

NEW： We provide saliency maps of of all compared methods in paper. baidu 提取码：zust or Google drive. <br>

Test saliency maps in all datasets[predict]: baidu 提取码：vy3r or Google drive. <br>

The pretrained model can be downloaded at[APNet.pth]: baidu 提取码：vy3r or Google drive.<br>

PS: we resize the testing data to the size of 224 * 224 for quicky evaluate[GT for matlab], baidu 提取码：vy3r or Google drive.<br>

Citation

@ARTICLE <br> {9583676, author={Zhou, Wujie and Zhu, Yun and Lei, Jingsheng and Wan, Jian and Yu, Lu}, <br> journal={IEEE Transactions on Emerging Topics in Computational Intelligence}, <br> title={APNet: Adversarial Learning Assistance and Perceived Importance Fusion Network for All-Day RGB-T Salient Object Detection}, <br> year={2021}, <br> volume={}, <br> number={}, <br> pages={1-12}, <br> doi={10.1109/TETCI.2021.3118043}}

Acknowledgement

The implement of this project is based on the code of ‘Cascaded Partial Decoder for Fast and Accurate Salient Object Detection, CVPR2019’and 'BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network' proposed by Wu et al and Deng et al.

Contact

Please drop me an email for further problems or discussion: zzzyylink@gmail.com or wujiezhou@163.com