研究发现生成式AI并不受经典图像影响，难以复现标志性视觉作品。
The Iconicity of the Generated Image
- 通过数据归属、语义相似度和用户实验三方面分析图标对生成模型的影响。
- 多数标志性图像无法在生成结果中被准确还原，影响不明显。
- 揭示人类与AI在视觉学习机制上的根本差异，适合关注生成模型局限的研究者。
人类对图像的理解与创作受过往视觉经验影响。类似地，视觉生成AI模型在大量训练图像基础上学习生成新图像。鉴于标志性图像在人类视觉交流中的广泛传播与影响力，我们推测它们可能在生成模型中也具有显著作用。本文通过三部分分析——数据归属、语义相似性分析及用户研究——探讨这一假设。结果表明，标志性图像对生成过程并无明显影响，且许多经典图像难以被模型准确再现。这揭示了人类与视觉生成AI在借鉴与学习既有视觉内容方面的关键差异。
原文摘要 · Abstract (English)
How humans interpret and produce images is influenced by the images we have been exposed to. Similarly, visual generative AI models are exposed to many training images and learn to generate new images based on this. Given the importance of iconic images in human visual communication, as they are widely seen, reproduced, and used as inspiration, we may expect that they may similarly have a proportionally large influence within the generative AI process. In this work we explore this question through a three-part analysis, involving data attribution, semantic similarity analysis, and a user-study. Our findings indicate that iconic images do not have an obvious influence on the generative process, and that for many icons it is challenging to reproduce an image which resembles it closely. This highlights an important difference in how humans and visual generative AI models draw on and learn from prior visual communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。