重新审视图像质量评估中的知识迁移：感知偏好结构对齐视角
Rethinking Knowledge Transfer in Image Quality Assessment: A Perceptual Preference Structure Alignment Perspective
对做IQA或任何需要跨数据集迁移的视觉任务，PPR/PPC提供了一种无需训练、可解释的源数据筛选准则：用视觉特征与质量分数的相关性刻画数据集特有的偏好结构，再据此挑选与目标域偏好结构一致的源样本，可直接用于跨域微调前的数据选择。
原文依据 we propose Perceptual Preference Representation (PPR), which characterizes dataset-specific perceptual preference structures
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着成像场景快速多样化，图像质量评估（IQA）面临一个关键挑战：如何有效地将已有标注数据集中的感知知识迁移出去，以保证在新场景中实现可靠的质量预测。然而，当前的IQA模型难以泛化：直接迁移往往导致严重的性能下降，而多数据集联合训练很少带来稳定增益，甚至可能损害目标性能。在本工作中，我们识别出感知偏好结构失配是IQA迁移失败背后一个重要且尚未被充分探索的因素。在不同源数据集上训练的模型可能依赖不同的感知线索，从而导致条件分布P(Y|X)出现差异，阻碍有效迁移。为解决这一问题，我们提出感知偏好表征（PPR），通过分析视觉特征与质量分数之间的相关性来刻画数据集特有的感知偏好结构。基于PPR，我们定义感知偏好一致性（PPC），这是一种无需训练且可解释的度量，用于衡量不同数据集之间相对偏好的兼容性。在此基础上，我们开发了偏好结构对齐迁移（PreSTA），它选择在感知偏好结构上与目标域更对齐的源样本。大量实验表明，PreSTA在跨域、域内以及定向联合迁移设置下均取得更优性能，同时仅使用一小部分源数据。这些结果凸显出：对齐感知偏好结构，而非单纯增大数据集规模，才是IQA中实现有效且数据高效的知识迁移的关键。代码将公开于 https://github.com/Li-aobo/PreSTA。
英文原文摘要 1776 字符
As imaging scenarios diversify rapidly, Image Quality Assessment (IQA) faces a key challenge: how to effectively transfer perceptual knowledge from existing annotated datasets to ensure reliable quality prediction in new scenarios. However, current IQA models struggle to generalize: direct transfer often leads to severe performance degradation, while multi-dataset joint training rarely yields stable gains and can even harm target performance. In this work, we identify perceptual preference structure mismatch as an important and underexplored factor behind transfer failure in IQA. Models trained on different source datasets may rely on different perceptual cues, leading to discrepancies in the conditional distribution P(Y|X) that hinder effective transfer. To address this, we propose Perceptual Preference Representation (PPR), which characterizes dataset-specific perceptual preference structures by analyzing correlations between visual features and quality scores. Based on PPR, we define Perceptual Preference Consistency (PPC), a training-free and interpretable measure of relative preference compatibility across datasets. Building on this, we develop Preference-Structure-Aligned Transfer (PreSTA), which selects source samples better aligned with the target domain in terms of perceptual preference structure. Extensive experiments show that PreSTA achieves superior performance across cross-domain, within-domain, and targeted joint transfer settings while using only a small fraction of source data. These results highlight that aligning perceptual preference structures, rather than simply increasing dataset size, is crucial for effective and data-efficient knowledge transfer in IQA. Code will be publicly available at https://github.com/Li-aobo/PreSTA.