I2-Multimedia-Lab/SaTQA

[AAAI 2024] Transformer-Based No-Reference Image Quality Assessment via Supervised Contrastive Learning

Python

Transformer-Based No-Reference Image Quality Assessment via Supervised Contrastive Learning (AAAI 2024)

Environment

$ pip install -r requirements.txt

$ conda env create -f environment.yaml

Datasets

In this work we use 6 datasets (LIVE, CSIQ, TID2013, KADID10K, LIVE challenge, KonIQ, LIVEFB)

Training

SCL pre-training.
```
$ python train_scl.py
```
Final model for score prediction.
```
$ python train.py
```

Citation

If our work is useful for your research, please consider citing:

@inproceedings{shi2023transformer,
    author = {Shi, Jinsnog and Pan, Gao and Qin Jie},
    title = {Transformer-Based No-Reference Image Quality Assessment via Supervised Contrastive Learning},
    booktitle = {AAAI},
    year = {2024}
}