论文标题
通过区分概率程序来设计知觉难题
Designing Perceptual Puzzles by Differentiating Probabilistic Programs
论文作者
论文摘要
我们通过为人类感知的原则模型找到“对抗性示例”来设计新的视觉幻象 - 特别是对于概率模型，这些模型将视力视为贝叶斯推断。为了有效地执行此搜索，我们设计了一种可区分的概率编程语言，其API将MCMC推断作为一流的可区分功能。我们通过自动对人类视力的三个特征构成幻想来演示我们的方法：颜色恒定，大小恒定和面部感知。
We design new visual illusions by finding "adversarial examples" for principled models of human perception -- specifically, for probabilistic models, which treat vision as Bayesian inference. To perform this search efficiently, we design a differentiable probabilistic programming language, whose API exposes MCMC inference as a first-class differentiable function. We demonstrate our method by automatically creating illusions for three features of human vision: color constancy, size constancy, and face perception.
