Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?
Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?
复制标题
DOI：
10.48550/arxiv.2301.11722
复制
发表时间：
2023-01
期刊：
影响因子：
--
通讯作者：
Victor Boutin;Thomas Fel;Lakshya Singhal;Rishav Mukherji;Akash Nagaraj;Julien Colin;Thomas Serre
中科院分区：
文献类型：
--
作者：
Victor Boutin;Thomas Fel;Lakshya Singhal;Rishav Mukherji;Akash Nagaraj;Julien Colin;Thomas Serre
人工智能的一个重要里程碑是开发出可以产生与人类无法区分的绘图的算法。在这里，我们采用了Boutin等人（2022）的“多样性与可识别性”评分框架，发现一次性扩散模型确实已经开始缩小人类和机器之间的差距。然而，使用更细粒度的措施，个别样本的原创性，我们表明，加强指导的扩散模型有助于提高他们的图纸的人性化，但他们仍然达不到近似的原创性和可识别性的人类图纸。通过在线心理物理学实验收集的人类类别诊断特征与来自扩散模型的特征进行比较，发现人类依赖更少且更本地化的特征。总的来说，我们的研究表明，扩散模型大大帮助提高了机器生成的图纸的质量;然而，人类和机器之间的差距仍然存在-部分原因是视觉策略的差异。
An important milestone for AI is the development of algorithms that can produce drawings that are indistinguishable from those of humans. Here, we adapt the 'diversity vs. recognizability' scoring framework from Boutin et al, 2022 and find that one-shot diffusion models have indeed started to close the gap between humans and machines. However, using a finer-grained measure of the originality of individual samples, we show that strengthening the guidance of diffusion models helps improve the humanness of their drawings, but they still fall short of approximating the originality and recognizability of human drawings. Comparing human category diagnostic features, collected through an online psychophysics experiment, against those derived from diffusion models reveals that humans rely on fewer and more localized features. Overall, our study suggests that diffusion models have significantly helped improve the quality of machine-generated drawings; however, a gap between humans and machines remains -- in part explainable by discrepancies in visual strategies.