视觉-语言模型如何编码个性化图像审美评估？
What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?
AI总结：
本文分析了视觉-语言模型内部表示中审美属性的分布，利用这些属性实现轻量级个性化图像审美评估，无需微调模型。
摘要：
个性化图像审美评估（PIAA）是一个重要的研究问题，具有实际应用价值。尽管基于视觉-语言模型（VLMs）的方法被认为是PIAA的有力候选，但尚不清楚它们是否内部编码丰富的、多级的审美属性以实现有效的个性化。本文首先分析VLMs的内部表示，以检查这些审美属性的存在和分布，并利用它们进行轻量级、个体层面的个性化，而无需模型微调。我们的分析揭示了VLMs编码了多样化的审美属性，这些属性传播到语言解码器层。基于这些表示，我们证明简单的线性模型可以有效执行PIAA。我们进一步分析了审美信息如何在不同VLM架构和图像领域中跨层传输。我们的发现为如何利用VLMs建模主观、个体审美偏好提供了见解。我们的代码可在https://github.com/ynklab/vlm-latent-piaa获取。
英文摘要：
Personalized image aesthetics assessment (PIAA) is an important research problem with practical real-world applications. While methods based on vision-language models (VLMs) are promising candidates for PIAA, it remains unclear whether they internally encode rich, multi-level aesthetic attributes required for effective personalization. In this paper, we first analyze the internal representations of VLMs to examine the presence and distribution of such aesthetic attributes, and then leverage them for lightweight, individual-level personalization without model fine-tuning. Our analysis reveals that VLMs encode diverse aesthetic attributes that propagate into the language decoder layers. Building on these representations, we demonstrate that simple linear models can perform PIAA effectively. We further analyze how aesthetic information is transferred across layers in different VLM architectures and across image domains. Our findings provide insights into how VLMs can be utilized for modeling subjective, individual aesthetic preferences. Our code is available at https://github.com/ynklab/vlm-latent-piaa.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
