Designing Perceptual Puzzles by Differentiating Probabilistic Programs

Autor:	Kartik Chandra, Tzu-Mao Li, Joshua Tenenbaum, Jonathan Ragan-Kelley
Jazyk:	angličtina
Rok vydání:	2022
Předmět:	FOS: Computer and information sciences Computer Science - Machine Learning Artificial Intelligence (cs.AI) Computer Science - Graphics Computer Science - Artificial Intelligence Graphics (cs.GR) Machine Learning (cs.LG)
Popis:	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. 9 pages; 3 figures; SIGGRAPH '22 Conference Proceedings
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ee9ce0123c28c35d282181885d581ec7 http://arxiv.org/abs/2204.12301 Zobrazit plný text záznamu