Saved in:
Bibliographic Details
Main Authors: Jones, R. Kenny, Chaudhuri, Siddhartha, Ritchie, Daniel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.15476
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929379981918208
author Jones, R. Kenny
Chaudhuri, Siddhartha
Ritchie, Daniel
author_facet Jones, R. Kenny
Chaudhuri, Siddhartha
Ritchie, Daniel
contents 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 Template Programs directly from visual datasets that contain concept groupings. We run experiments across multiple visual domains: 2D layouts, Omniglot characters, and 3D shapes. We find that our method outperforms task-specific alternatives, and performs competitively against domain-specific approaches for the limited domains where they exist.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15476
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning to Infer Generative Template Programs for Visual Concepts
Jones, R. Kenny
Chaudhuri, Siddhartha
Ritchie, Daniel
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
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 Template Programs directly from visual datasets that contain concept groupings. We run experiments across multiple visual domains: 2D layouts, Omniglot characters, and 3D shapes. We find that our method outperforms task-specific alternatives, and performs competitively against domain-specific approaches for the limited domains where they exist.
title Learning to Infer Generative Template Programs for Visual Concepts
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
url https://arxiv.org/abs/2403.15476