HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

The paper has been online published by IEEE Transactions on Circuits and Systems for Video Technology. https://ieeexplore.ieee.org/document/9869666

paper

main

Training Set

2185 https://drive.google.com/file/d/1fcJj4aYdJ6N-TvvxSZ_sBo-xhtd_w-eJ/view?usp=sharing

2985 https://drive.google.com/file/d/1mYjaT_FTlY4atd-c0WdQ-0beZIpf8fgh/view?usp=sharing

Testing Set

Google https://drive.google.com/file/d/1dQWrhO-LHVACDKCTrvdc6eIbcyH7Yzp_/view?usp=sharing

Baidu:https://pan.baidu.com/s/1fN-AsBiKTbMRsye0Lr8K7g 提取码:l2u9

Pretraining Parameter

Our RGB-D SOD Parameters:

2185 链接:https://pan.baidu.com/s/1SFxvnHLd8iJ8eARI4oJw0w 提取码:pbrg

2985 链接:https://pan.baidu.com/s/1UspJOEnhvIge8_heQDF55A 提取码:e7ca

Our RGB-T SOD Parameter: 链接:https://pan.baidu.com/s/1sEKEMGYKJD9eT-bvUxvamA 提取码:jhkb

Our LF SOD Parameter: 链接:https://pan.baidu.com/s/1hPUQLM0U-s9mzVDVor27iA 提取码:d459

RGBD Result Saliency Maps

链接:https://pan.baidu.com/s/12JcJK5RY7km7RtMWVPii7Q 提取码:1615

RGBT Result Saliency Maps

链接:https://pan.baidu.com/s/1b3RhH_2M0s3T8EMFWu-Apg 提取码:n5zc

LF Result Saliency Maps

链接:https://pan.baidu.com/s/1IRR5aO8ViEz7BYX89R1AEA 提取码:hr1j

Evaluation Code

Google: https://drive.google.com/file/d/1-fXbORnXNVfvm7uarXLX6w9PuVhs-25d/view?usp=sharing

Baidu:https://pan.baidu.com/s/1EtKTNVPQAW_iLm8pA1POmQ 提取码:86gt

Citation

If you find the information useful, please consider citing:

@article{Tang2023RTransNet,
  author={Tang, Bin and Liu, Zhengyi and Tan, Yacheng and He, Qian},
  journal={IEEE Transactions on Circuits and Systems for Video Technology}, 
  title={HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection}, 
  pages={728--742},
  year={2023}}

If you have any question, please email liuzywen@ahu.edu.cn