UTA

The PyTorch implementation of RGB-D Salient Object Detection with Ubiquitous Target Awareness.

NOTE: UTA is an extension work of DASNet.

Prerequisites

• python=3.7
• pytorch==1.6.0
• torchvision=0.7.0
• apex==0.1
• opencv-python==4.2

Dir

• res: resnet pre-trained models
• eval: test results
• data: datasets
• checkpoint: models

Datasets

• Train data
• Test data
• Test results

Model

• Download the model into checkpoint folder.

Train

cd src
python train_UTA.py

Test

cd src
python test.py

Evaluation

cd eval
matlab
main

Citation

• If you find this work is helpful, please cite our paper

@ARTICLE{zhao2021UTA,
  author={Zhao, Yifan and Zhao, Jiawei and Li, Jia and Chen, Xiaowu},
  journal={IEEE Transactions on Image Processing}, 
  title={RGB-D Salient Object Detection With Ubiquitous Target Awareness}, 
  year={2021},
  volume={30},
  number={},
  pages={7717-7731},
  doi={10.1109/TIP.2021.3108412}}

Reference

This project is based on the following implementations:

• https://github.com/iCVTEAM/DASNet