NobleBlocks
Public

Visual Programming: Compositional visual reasoning without training

Published in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) • Jun 1, 2023
NobleIDNI6P87W33R62S00
Authors:
Tanmay Gupta
,
Aniruddha Kembhavi

Abstract

We present Visprog, a neuro-symbolic approach to solving complex and compositional visual tasks given natural language instructions. Visprog avoids the need for any task-specific training. Instead, it uses the incontext learning ability of large language models to generate python-like modular progra...

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!