---
license: mit
language:
- en
base_model:
- MAGAer13/mplug-owl2-llama2-7b
---

# DeQA-Score-LoRA-Mix3

DeQA-Score (
[project page](https://depictqa.github.io/deqa-score/) / 
[codes](https://github.com/zhiyuanyou/DeQA-Score) / 
[paper](https://arxiv.org/abs/2501.11561) 
) model weights LoRA fine-tuned on KonIQ, SPAQ, and KADID datasets. 

This work is under our [DepictQA project](https://depictqa.github.io/).

## Non-reference IQA Results (PLCC / SRCC)

| | Fine-tune | KonIQ     | SPAQ     | KADID    | PIPAL    | LIVE-Wild | AGIQA    | TID2013  | CSIQ     |
|--------------|-----------|-----------|----------|----------|----------|-----------|----------|----------|----------|
| Q-Align (Baseline) | Fully | 0.945 / 0.938 | 0.933 / 0.931 | 0.935 / 0.934 | 0.409 / 0.420 | 0.887 / 0.883 | 0.788 / 0.733 | 0.829 / 0.808 | 0.876 / 0.845 |
| DeQA-Score (Ours) | LoRA | **0.956 / 0.944** | **0.939 / 0.935** | **0.953 / 0.951** | **0.481 / 0.481** | **0.903 / 0.890** | **0.806 / 0.754** | **0.851 / 0.821** | **0.900 / 0.860** |

If you find our work useful for your research and applications, please cite using the BibTeX:

```bibtex
@article{deqa_score,
  title={Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution},
  author={You, Zhiyuan and Cai, Xin and Gu, Jinjin and Xue, Tianfan and Dong, Chao},
  journal={arXiv preprint arXiv:2501.11561},
  year={2025},
}
```