With the advancement of generative models, the assessment of generated images becomes more and more important. Previous methods measure distances between features of reference and generated images from trained vision models. In this paper, we conduct an extensive investigation into the relationship between the representation space and input space around generated images. We first propose two measures related to the presence of unnatural elements within images: complexity, which indicates how non-linear the representation space is, and vulnerability, which is related to how easily the extracted feature changes by adversarial input changes. Based on these, we introduce a new metric to evaluating image-generative models called anomaly score (AS). Moreover, we propose AS-i (anomaly score for individual images) that can effectively evaluate generated images individually. Experimental results demonstrate the validity of the proposed approach.

翻译：随着生成模型的进步，生成图像的评价变得越来越重要。以往的方法通过训练好的视觉模型，度量参考图像与生成图像特征之间的距离。本文围绕生成图像附近的表示空间与输入空间之间的关系展开了深入研究。我们首先提出了两种与图像中非自然元素存在相关的度量指标：复杂性，用于描述表示空间的非线性程度；以及脆弱性，用于表征提取特征因对抗性输入变化而改变的难易程度。基于这些指标，我们引入了一种名为异常评分（AS）的新指标来评估图像生成模型。此外，我们还提出了AS-i（单个图像异常评分），能够有效对单个生成图像进行评价。实验结果验证了所提方法的有效性。