面向统一图像美学与质量评估的概率提示词适配
Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment
把「提示词选择」建模为对 LLM 预采样提示词集合的混合分布并做边缘化，使视觉语言模型能在只有 (任务, 图像, 分数) 三元组、无标注的情况下适配任意文本提示词；做文本条件评分或提示词敏感任务时可复用这一概率化提示词适配思路。
原文依据 PPA formulates score prediction as a mixture over prompts, dynamically estimating prompt suitability based on both image content and task context.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期视觉语言基础模型的进展使文本驱动的图像美学与视觉质量评估成为可能。然而，现有模型通常针对固定提示词或特定数据集进行优化，限制了其对多样评估标准的适应能力。本文提出概率提示词适配（PPA），这是一个统一的概率框架，能够以任意文本提示词为条件，灵活预测美学分数与质量分数。PPA 将分数预测建模为提示词上的混合，依据图像内容与任务上下文动态估计提示词的适用性。通过对由大语言模型（LLM）预先采样的提示词进行边缘化，它仅使用任务、图像与分数构成的三元组即可实现无标注训练。在多个 IAA 与 IQA 基准上的实验表明，PPA 实现了连贯且与感知一致的基于提示词的评分，并能够对评估语义进行细粒度控制。
英文原文摘要 964 字符
Recent advances in vision-language foundation models have enabled text-driven evaluation of image aesthetics and visual quality. However, existing models are typically optimized for fixed prompts or specific datasets, limiting their adaptability to diverse evaluation criteria. This paper presents Probabilistic Prompt Adaptation (PPA), a unified probabilistic framework that flexibly predicts aesthetic and quality scores conditioned on arbitrary text prompts. PPA formulates score prediction as a mixture over prompts, dynamically estimating prompt suitability based on both image content and task context. By marginalizing over prompts pre-sampled from a large language model (LLM), it enables annotation-free training using only triplets of task, image, and score. Experiments across multiple IAA and IQA benchmarks demonstrate that PPA achieves consistent and perceptually aligned prompt-based scoring, allowing fine-grained control over evaluation semantics.