Image captioning for effective use of language models in knowledge-based visual question answering

Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal (text-only) train and inference procedure based on automati...

Descripción completa

Detalles Bibliográficos
Autores: Salaberria Saizar, Ander, Azkune Galparsoro, Gorka, López de Lacalle Lecuona, Oier, Soroa Echave, Aitor, Agirre Bengoa, Eneko
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:addi.ehu.eus:10810/59873
Acceso en línea:http://hdl.handle.net/10810/59873
Access Level:acceso abierto
Palabra clave:visual question answering
image captioning
language models
deep learning
Descripción
Sumario:Integrating outside knowledge for reasoning in visio-linguistic tasks such as visual question answering (VQA) is an open problem. Given that pretrained language models have been shown to include world knowledge, we propose to use a unimodal (text-only) train and inference procedure based on automatic off-the-shelf captioning of images and pretrained language models. More specifically, we verbalize the image contents and allow language models to better leverage their implicit knowledge to solve knowledge-intensive tasks. Focusing on a visual question answering task which requires external knowledge (OK-VQA), our contributions are: (i) a text-only model that outperforms pretrained multimodal (image-text) models of comparable number of parameters; (ii) confirmation that our text-only method is specially effective for tasks requiring external knowledge, as it is less effective in standard a VQA task (VQA 2.0); and (iii) our method attains results in the state-of-the-art when increasing the size of the language model. We also significantly outperform current multimodal systems, even though augmented with external knowledge. Our qualitative analysis on OK-VQA reveals that automatic captions often fail to capture relevant information in the images, which seems to be balanced by the better inference ability of the text-only language models. Our work opens up possibilities to further improve inference in visio-linguistic tasks.