SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yan, Lin, Jiaqing, Zhang, Miao, Xiao, Kui, Hou, Xiaoju, Zhao, Yue, Li, Zhifei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915513238552576
author Zhang, Yan
Lin, Jiaqing
Zhang, Miao
Xiao, Kui
Hou, Xiaoju
Zhao, Yue
Li, Zhifei
author_facet Zhang, Yan
Lin, Jiaqing
Zhang, Miao
Xiao, Kui
Hou, Xiaoju
Zhao, Yue
Li, Zhifei
contents Acquiring high-quality knowledge is a central focus in Knowledge-Based Visual Question Answering (KB-VQA). Recent methods use large language models (LLMs) as knowledge engines for answering. These methods generally employ image captions as visual text descriptions to assist LLMs in interpreting images. However, the captions frequently include excessive noise irrelevant to the question, and LLMs generally do not comprehend VQA tasks, limiting their reasoning capabilities. To address this issue, we propose the Summarized Caption-Rerank Augmented VQA (SCRA-VQA), which employs a pre-trained visual language model to convert images into captions. Moreover, SCRA-VQA generates contextual examples for the captions while simultaneously summarizing and reordering them to exclude unrelated information. The caption-rerank process enables LLMs to understand the image information and questions better, thus enhancing the model's reasoning ability and task adaptability without expensive end-to-end training. Based on an LLM with 6.7B parameters, SCRA-VQA performs excellently on two challenging knowledge-based VQA datasets: OK-VQA and A-OKVQA, achieving accuracies of 38.8% and 34.6%. Our code is available at https://github.com/HubuKG/SCRA-VQA.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20871
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering
Zhang, Yan
Lin, Jiaqing
Zhang, Miao
Xiao, Kui
Hou, Xiaoju
Zhao, Yue
Li, Zhifei
Computer Vision and Pattern Recognition
Artificial Intelligence
Acquiring high-quality knowledge is a central focus in Knowledge-Based Visual Question Answering (KB-VQA). Recent methods use large language models (LLMs) as knowledge engines for answering. These methods generally employ image captions as visual text descriptions to assist LLMs in interpreting images. However, the captions frequently include excessive noise irrelevant to the question, and LLMs generally do not comprehend VQA tasks, limiting their reasoning capabilities. To address this issue, we propose the Summarized Caption-Rerank Augmented VQA (SCRA-VQA), which employs a pre-trained visual language model to convert images into captions. Moreover, SCRA-VQA generates contextual examples for the captions while simultaneously summarizing and reordering them to exclude unrelated information. The caption-rerank process enables LLMs to understand the image information and questions better, thus enhancing the model's reasoning ability and task adaptability without expensive end-to-end training. Based on an LLM with 6.7B parameters, SCRA-VQA performs excellently on two challenging knowledge-based VQA datasets: OK-VQA and A-OKVQA, achieving accuracies of 38.8% and 34.6%. Our code is available at https://github.com/HubuKG/SCRA-VQA.
title SCRA-VQA: Summarized Caption-Rerank for Augmented Large Language Models in Visual Question Answering
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.20871