Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering

2026-08-19

AI Summary

为解决视觉相似性与实体语义一致性之间的矛盾，提出KBMR方法，利用多模态大语言模型生成语义嵌入和一致性权重，提升知识库视觉问答的检索精度。

Abstract

Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, existing retrieval pipelines predominantly employ CLIP-style dual encoders, which prioritize surface-level visual similarity over entity-level semantic alignment. This paradigm often fails when semantically identical concepts exhibit large visual variations or when distinct entities appear visually similar. To address this, we propose KBMR, the first MLLM-based embedding retriever tailored for KB-VQA. Leveraging the robust autoregressive capabilities of MLLMs, KBMR maps images into a semantic space that better preserves concept identity. To tackle the challenge of noisy supervision in Wikipedia-scale retrieval, we introduce an MLLM-based semantic discriminator that generates continuous entity-consistency weights. These weights guide a novel continuous semantic distillation objective, enabling effective hard negative sampling and soft supervision beyond rigid binary labels. Extensive experiments demonstrate that KBMR significantly outperforms CLIP baselines, yielding up to a 14.7% improvement in retrieval Recall@1 and a 9.4% gain in end-to-end VQA accuracy. Code is available at https://github.com/realHarryX/KBMR.

Problem

• Knowledge-Based Visual Question Answering
• entity-level semantic alignment
• visual similarity

Innovation

• MLLM-based embedding retriever
• semantic space
• entity-consistency weights
• continuous semantic distillation