Modelpublic

RobinY99/MR-IQA

sourceHugging Facemitupdated 3mo agoView on Hugging Face

0likes7downloads

Model Card

MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment

<p align="center"> <a href="https://arxiv.org/abs/2606.29760">arXiv</a> | <a href="https://github.com/RobinY99/MR-IQA">GitHub</a> </p>

We derive that regression and ranking are approximately equivalent under a unified margin view. Based on this observation, we propose MR-IQA for margin learning in blind image quality assessment.

Validation Snapshot

The released checkpoint was validated after each epoch with an 8-shard setup on a held-out KONIQ split.

Epoch	Valid samples	SRCC	PLCC	Shards
1	200	0.8840	0.8894	8
2	200	0.9213	0.9302	8
3	200	0.9318	0.9392	8
4	200	0.9274	0.9340	8
5	200	0.9271	0.9409	8
6	200	0.9249	0.9406	8
7	200	0.9205	0.9408	8
8	200	0.9288	0.9465	8
9	200	0.9307	0.9450	8
10	200	0.9251	0.9421	8

Best SRCC was reached at epoch 3. The final released checkpoint corresponds to epoch 10. Sanitized training metadata is available in `training_guidance/`.

Quick Start

Load the model with a standard Transformers vision-language workflow. The training and evaluation code use a no-reasoning prompt and parse the final numeric score from <answer>...</answer>.

System prompt:

text

You are an image quality assessment assistant. Output only the final score in <answer> </answer> tags.

User prompt:

text

What is your overall rating on the quality of this picture? The rating should be a float between 1 and 5, rounded to two decimal places, with 1 representing very poor quality and 5 representing excellent quality. Please only output the final answer with one score in <answer> </answer> tags.

Output Format

The expected response is only one score in answer tags:

text

<answer>3.74</answer>

The evaluation parser first reads the number inside <answer>...</answer> and clamps valid scores to the 1 to 5 range.

Citation

bibtex

@misc{li2026mriqaunifiedmarginview,
  title={MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment},
  author={Yuan Li and Youyuan Lin and Zitang Sun and Yung-Hao Yang and Kiyofumi Miyoshi and Chenhui Chu and Shin'ya Nishida},
  year={2026},
  eprint={2606.29760},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2606.29760}
}