Skip to content
/ ADTRS Public

Attention Down-Sampling Transformer, Relative Ranking And Self-Consistency for Blind Image Quality Assessment

License

Notifications You must be signed in to change notification settings

MAS94/ADTRS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ADTRS

The source code for the ICIP 2024 paper titled 'Attention Down-Sampling Transformer, Relative Ranking, and Self-Consistency for Blind Image Quality Assessment'.

Requirements

The model is built using

  • Python 3.7
  • PyTorch 1.7.0+cu110
  • TorchVision 0.8.0
  • scipy
  • numpy

Datasets

In this study, we utilize five datasets for evaluation (LIVE, CLIVE, TID2013, CSIQ, KonIQ)

In the run.py file, update the folderpath to match the name of the dataset folder within the project directory.

Acknowledgement

This code incorporates components from TReS and EfficientFormer.

Citation

If you find the code helpful in your research or work, please cite the following paper.

@INPROCEEDINGS{10647621,
  author={Alsaafin, Mohammed and Alsheikh, Musab and Anwar, Saeed and Usman, Muhammad},
  booktitle={2024 IEEE International Conference on Image Processing (ICIP)}, 
  title={Attention Down-Sampling Transformer, Relative Ranking and Self-Consistency For Blind Image Quality Assessment}, 
  year={2024},
  volume={},
  number={},
  pages={1260-1266},
  keywords={Image quality;Degradation;Adaptation models;Visualization;Image transformation;Transformers;Feature extraction;No-Reference Image Quality Assessment;CNNs;Transformers;Self-Consistency;Relative Ranking},
  doi={10.1109/ICIP51287.2024.10647621}}

About

Attention Down-Sampling Transformer, Relative Ranking And Self-Consistency for Blind Image Quality Assessment

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages