Learning to Infer Generative Template Programs for Visual Concepts

arXiv:2403.15476v1 Announce Type: cross
Abstract: People grasp flexible visual concepts from a few examples. We explore a neurosymbolic system that learns how to infer programs that capture visual concepts in a domain-general fashion. We introduce Template Programs: programmatic expressions from a domain-specific language that specify structural and parametric patterns common to an input concept. Our framework supports multiple concept-related tasks, including few-shot generation and co-segmentation through parsing. We develop a learning paradigm that allows us to train networks that infer …

abstract arxiv concepts cs.ai cs.cv cs.gr cs.lg domain examples explore fashion general generative language parametric patterns people programmatic template type visual visual concepts