.png){kind=icon}
返回
Zero-shot visual reasoning through probabilistic analogical mapping
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-023-40804-x.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require extensive direct training on visual reasoning tasks, and yield limited generalization to problems with novel content. In contrast, a long tradition of research in cognitive science has focused on elucidating the computational principles underlying human analogical reasoning; however, this work has generally relied on manually constructed representations. Here we present visiPAM (visual Probabilistic Analogical Mapping), a model of visual reasoning that synthesizes these two approaches. VisiPAM employs learned representations derived directly from naturalistic visual inputs, coupled with a similarity-based mapping operation derived from cognitive theories of human reasoning. We show that without any direct training, visiPAM outperforms a state-of-the-art deep learning model on an analogical mapping task. In addition, visiPAM closely matches the pattern of human performance on a novel task involving mapping of 3D objects across disparate categories.
Keyword:
SIMILARITY
ALGORITHM
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
15.7
论文数:
9.4W
被引数:
91.2W
机构
引用论文
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏Exergy Load Distribution Analysis Applied to the Dehydration of Ethanol by Extractive Distillation.png)
Energies
OAAI
EnergiesIF0
OAAI分享收藏Distributed representations of structure: A theory of analogical access and mappingPSYCHOLOGICAL REVIEW
PSYCHOLOGICAL REVIEWIF5.8
PREAI
分享收藏分享收藏
查看更多内容