Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sampat, Shailaja Keyur, Patel, Maitreya, Yang, Yezhou, Baral, Chitta
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912075469553664
author Sampat, Shailaja Keyur
Patel, Maitreya
Yang, Yezhou
Baral, Chitta
author_facet Sampat, Shailaja Keyur
Patel, Maitreya
Yang, Yezhou
Baral, Chitta
contents An ability to learn about new objects from a small amount of visual data and produce convincing linguistic justification about the presence/absence of certain concepts (that collectively compose the object) in novel scenarios is an important characteristic of human cognition. This is possible due to abstraction of attributes/properties that an object is composed of e.g. an object `bird' can be identified by the presence of a beak, feathers, legs, wings, etc. Inspired by this aspect of human reasoning, in this work, we present a zero-shot framework for fine-grained visual concept learning by leveraging large language model and Visual Question Answering (VQA) system. Specifically, we prompt GPT-3 to obtain a rich linguistic description of visual objects in the dataset. We convert the obtained concept descriptions into a set of binary questions. We pose these questions along with the query image to a VQA system and aggregate the answers to determine the presence or absence of an object in the test images. Our experiments demonstrate comparable performance with existing zero-shot visual classification methods and few-shot concept learning approaches, without substantial computational overhead, yet being fully explainable from the reasoning perspective.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13651
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?
Sampat, Shailaja Keyur
Patel, Maitreya
Yang, Yezhou
Baral, Chitta
Computer Vision and Pattern Recognition
An ability to learn about new objects from a small amount of visual data and produce convincing linguistic justification about the presence/absence of certain concepts (that collectively compose the object) in novel scenarios is an important characteristic of human cognition. This is possible due to abstraction of attributes/properties that an object is composed of e.g. an object `bird' can be identified by the presence of a beak, feathers, legs, wings, etc. Inspired by this aspect of human reasoning, in this work, we present a zero-shot framework for fine-grained visual concept learning by leveraging large language model and Visual Question Answering (VQA) system. Specifically, we prompt GPT-3 to obtain a rich linguistic description of visual objects in the dataset. We convert the obtained concept descriptions into a set of binary questions. We pose these questions along with the query image to a VQA system and aggregate the answers to determine the presence or absence of an object in the test images. Our experiments demonstrate comparable performance with existing zero-shot visual classification methods and few-shot concept learning approaches, without substantial computational overhead, yet being fully explainable from the reasoning perspective.
title Help Me Identify: Is an LLM+VQA System All We Need to Identify Visual Concepts?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.13651