DeQA-Score-LoRA-Mix3

DeQA-Score ( project page / codes / paper ) model weights LoRA fine-tuned on KonIQ, SPAQ, and KADID datasets.

This work is under our DepictQA project.

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:

@inproceedings{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},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2025},
}