MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Shuo, Luo, Siwen, Han, Soyeon Caren, Hovy, Eduard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908403287195648
author Yang, Shuo
Luo, Siwen
Han, Soyeon Caren
Hovy, Eduard
author_facet Yang, Shuo
Luo, Siwen
Han, Soyeon Caren
Hovy, Eduard
contents Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limiting their robustness in real-world scenarios. To address this, we introduce MAGIC-VQA, a novel framework that enhances VQA by systematically integrating commonsense knowledge with LVLMs. MAGIC-VQA employs a three-stage process: (1) Explicit Knowledge Integration from external sources, (2) By-Type Post-Processing for contextual refinement, and (3) Implicit Knowledge Augmentation using a Graph Neural Network (GNN) for structured reasoning. While GNNs bring greater depth to structured inference, they enable superior relational inference beyond LVLMs. MAGIC-VQA bridges a key gap by unifying commonsensse knowledge with LVLM-driven reasoning, eliminating the need for extensive pre-training or complex prompt tuning. Our framework achieves state-of-the-art performance on benchmark datasets, significantly improving commonsense reasoning in VQA.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18491
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering
Yang, Shuo
Luo, Siwen
Han, Soyeon Caren
Hovy, Eduard
Computation and Language
Visual Question Answering (VQA) requires reasoning across visual and textual modalities, yet Large Vision-Language Models (LVLMs) often lack integrated commonsense knowledge, limiting their robustness in real-world scenarios. To address this, we introduce MAGIC-VQA, a novel framework that enhances VQA by systematically integrating commonsense knowledge with LVLMs. MAGIC-VQA employs a three-stage process: (1) Explicit Knowledge Integration from external sources, (2) By-Type Post-Processing for contextual refinement, and (3) Implicit Knowledge Augmentation using a Graph Neural Network (GNN) for structured reasoning. While GNNs bring greater depth to structured inference, they enable superior relational inference beyond LVLMs. MAGIC-VQA bridges a key gap by unifying commonsensse knowledge with LVLM-driven reasoning, eliminating the need for extensive pre-training or complex prompt tuning. Our framework achieves state-of-the-art performance on benchmark datasets, significantly improving commonsense reasoning in VQA.
title MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering
topic Computation and Language
url https://arxiv.org/abs/2503.18491