Visual Programming: Compositional visual reasoning without training

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...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 14953 - 14962
Main Authors: Gupta, Tanmay, Kembhavi, Aniruddha
Format: Conference Proceeding
Language:English
Published: IEEE 01.06.2023
Subjects:
and reasoning
Computational modeling
Computer vision
language
Programming
Tagging
Tail
Training
Vision
Visualization
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 programs, which are then executed to get both the solution and a comprehensive and interpretable rationale. Each line of the generated program may invoke one of several off-the-shelf computer vision models, image processing subroutines, or python functions to produce intermediate outputs that may be consumed by subsequent parts of the program. We demonstrate the flexibility of VIsPROG on 4 diverse tasks - compositional visual question answering, zero-shot reasoning on image pairs, factual knowledge object tagging, and language-guided image editing. We believe neuro-symbolic approaches like Visprog are an exciting avenue to easily and effectively expand the scope of AI systems to serve the long tail of complex tasks that people may wish to perform.
ISSN:1063-6919
DOI:10.1109/CVPR52729.2023.01436