Reasoning-induced vision-language models (VLMs) advance image quality assessment (IQA) with textual reasoning, yet their scalar scores often lack sensitivity and collapse to a few values, so-called discrete collapse. We introduce ME-IQA, a plug-and-play, test-time memory-enhanced re-ranking framework. It (i) builds a memory bank and retrieves semantically and perceptually aligned neighbors using reasoning summaries, (ii) reframes the VLM as a probabilistic comparator to obtain pairwise preference probabilities and fuse this ordinal evidence with the initial score under Thurstone's Case V model, and (iii) performs gated reflection and consolidates memory to improve future decisions. This yields denser, distortion-sensitive predictions and mitigates discrete collapse. Experiments across multiple IQA benchmarks show consistent gains over strong reasoning-induced VLM baselines, existing non-reasoning IQA methods, and test-time scaling alternatives.
@article{arxiv.2603.20785,
title = {ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking},
author = {Kanglong Fan and Tianhe Wu and Wen Wen and Jianzhao Liu and Le Yang and Yabin Zhang and Yiting Liao and Junlin Li and Li Zhang},
journal= {arXiv preprint arXiv:2603.20785},
year = {2026}
}