Zero-shot visual reasoning through probabilistic analogical mapping.

ABSTRACT: 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 naturalis

SUBMITTER: Webb T 

PROVIDER: S-EPMC10449798 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature