Abduction of Domain Relationships from Data for VQA

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chowdhury, Al Mehdi Saadat, Shakarian, Paulo, Simari, Gerardo I.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912231023706112
author Chowdhury, Al Mehdi Saadat
Shakarian, Paulo
Simari, Gerardo I.
author_facet Chowdhury, Al Mehdi Saadat
Shakarian, Paulo
Simari, Gerardo I.
contents In this paper, we study the problem of visual question answering (VQA) where the image and query are represented by ASP programs that lack domain data. We provide an approach that is orthogonal and complementary to existing knowledge augmentation techniques where we abduce domain relationships of image constructs from past examples. After framing the abduction problem, we provide a baseline approach, and an implementation that significantly improves the accuracy of query answering yet requires few examples.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09219
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Abduction of Domain Relationships from Data for VQA
Chowdhury, Al Mehdi Saadat
Shakarian, Paulo
Simari, Gerardo I.
Logic in Computer Science
Artificial Intelligence
Machine Learning
In this paper, we study the problem of visual question answering (VQA) where the image and query are represented by ASP programs that lack domain data. We provide an approach that is orthogonal and complementary to existing knowledge augmentation techniques where we abduce domain relationships of image constructs from past examples. After framing the abduction problem, we provide a baseline approach, and an implementation that significantly improves the accuracy of query answering yet requires few examples.
title Abduction of Domain Relationships from Data for VQA
topic Logic in Computer Science
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2502.09219