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!