Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kim, Taehee, Cho, Yeongjae, Shin, Heejun, Jo, Yohan, Shin, Dongmyung
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917754966114304
author Kim, Taehee
Cho, Yeongjae
Shin, Heejun
Jo, Yohan
Shin, Dongmyung
author_facet Kim, Taehee
Cho, Yeongjae
Shin, Heejun
Jo, Yohan
Shin, Dongmyung
contents Visual question answering (VQA) is a task where an image is given, and a series of questions are asked about the image. To build an efficient VQA algorithm, a large amount of QA data is required which is very expensive. Generating synthetic QA pairs based on templates is a practical way to obtain data. However, VQA models trained on those data do not perform well on complex, human-written questions. To address this issue, we propose a new method called {\it chain of QA for human-written questions} (CoQAH). CoQAH utilizes a sequence of QA interactions between a large language model and a VQA model trained on synthetic data to reason and derive logical answers for human-written questions. We tested the effectiveness of CoQAH on two types of human-written VQA datasets for 3D-rendered and chest X-ray images and found that it achieved state-of-the-art accuracy in both types of data. Notably, CoQAH outperformed general vision-language models, VQA models, and medical foundation models with no finetuning.
format Preprint
id arxiv_https___arxiv_org_abs_2401_06400
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model
Kim, Taehee
Cho, Yeongjae
Shin, Heejun
Jo, Yohan
Shin, Dongmyung
Computation and Language
Computer Vision and Pattern Recognition
Visual question answering (VQA) is a task where an image is given, and a series of questions are asked about the image. To build an efficient VQA algorithm, a large amount of QA data is required which is very expensive. Generating synthetic QA pairs based on templates is a practical way to obtain data. However, VQA models trained on those data do not perform well on complex, human-written questions. To address this issue, we propose a new method called {\it chain of QA for human-written questions} (CoQAH). CoQAH utilizes a sequence of QA interactions between a large language model and a VQA model trained on synthetic data to reason and derive logical answers for human-written questions. We tested the effectiveness of CoQAH on two types of human-written VQA datasets for 3D-rendered and chest X-ray images and found that it achieved state-of-the-art accuracy in both types of data. Notably, CoQAH outperformed general vision-language models, VQA models, and medical foundation models with no finetuning.
title Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.06400