M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base

TL;DR

M^2ConceptBase is a comprehensive, concept-centric multimodal knowledge base that aligns detailed visual and textual semantics with concepts, significantly improving multimodal model understanding and performance on tasks like VQA.

Contribution

It introduces the first concept-centric MMKB with a novel context-aware grounding approach, linking concepts with images and descriptions for enhanced multimodal reasoning.

Findings

Over 95% alignment accuracy confirmed by human studies

Significant performance boost on OK-VQA task

Improves concept understanding in multimodal LLMs

Abstract

Multimodal knowledge bases (MMKBs) provide cross-modal aligned knowledge crucial for multimodal tasks. However, the images in existing MMKBs are generally collected for entities in encyclopedia knowledge graphs. Therefore, detailed groundings of visual semantics with linguistic concepts are lacking, which are essential for the visual concept cognition ability of multimodal models. Addressing this gap, we introduce M^2ConceptBase, the first concept-centric MMKB. M^2ConceptBase models concepts as nodes with associated images and detailed textual descriptions. We propose a context-aware multimodal symbol grounding approach to align concept-image and concept-description pairs using context information from image-text datasets. Comprising 951K images and 152K concepts, M^2ConceptBase links each concept to an average of 6.27 images and a single description, ensuring comprehensive visual and textual semantics. Human studies confirm more than 95% alignment accuracy, underscoring its quality. Additionally, our experiments demonstrate that M^2ConceptBase significantly enhances VQA model performance on the OK-VQA task. M^2ConceptBase also substantially improves the fine-grained concept understanding capabilities of multimodal large language models through retrieval augmentation in two concept-related tasks, highlighting its value.