美在观察者的证据下界（ELBO）中：面孔感知中加工流畅性的变分解释
Beauty is in the ELBO of the Beholder: A Variational Account of Processing Fluency in Face Perception
- Frankfurt Institute for Advanced Studies（法兰克福高等研究院）
- School of Computer Science and Engineering, UNSW Sydney（新南威尔士大学悉尼分校计算机科学与工程学院）
- Goethe University Frankfurt（法兰克福大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究通过训练变分自编码器，发现人类面孔吸引力评分与VAE的ELBO方向高度一致，为审美愉悦的加工流畅性理论提供了变分解释的实证支持。
AI中文摘要：
面部吸引力与对称性、平均性等统计规律相关，提示美可能取决于感知面孔的难易程度。我们在四个无吸引力监督的人脸数据集上训练变分自编码器（VAE），并在芝加哥人脸数据库（CFD）的597张人脸图像上评估其表征以实证检验该假设。在所有模型中，人类吸引力评分与率-失真空间中VAE证据下界（ELBO）定义的方向高度一致。独立学习的潜在空间包含一个吸引力方向，该方向在随机初始化和训练数据间具有强迁移性。我们还发现，有吸引力的面孔在形状和潜在空间中更具典型性。本研究将经典美学理论与学习生成模型关联，为审美愉悦的加工流畅性理论提供了变分解释的实证支持。
英文摘要：
Facial attractiveness has been linked to statistical regularities such as symmetry and averageness, suggesting that beauty may depend on the ease with which a face is perceived. We empirically test this hypothesis by training variational autoencoders on four face datasets without attractiveness supervision and evaluating their representations on the 597 faces from the Chicago Face Database. Across models, human attractiveness ratings closely aligns with the direction defined by the VAE evidence lower bound (ELBO) in rate-distortion space. Independently learned latent spaces contain an attractiveness direction that transfers strongly across random initializations and training data. We also find that attractive faces are more prototypical in both shape and latent space. Our results connect classic accounts of aesthetics with learned generative models and provide empirical support for a variational interpretation of the processing fluency theory of aesthetic pleasure.
