End-to-end Knowledge Retrieval With Multi-modal Queries

Abstract

We investigate knowledge retrieval with multi-modal queries, i.e. queries containing information split across image and text inputs, a challenging task that differs from previous work on cross-modal retrieval. We curate a new dataset called ReMuQ for benchmarking progress on this task. ReMuQ requires a system to retrieve knowledge from a large corpus by integrating contents from both text and image queries. We introduce a retriever model ``ReViz'' that can directly process input text and images to retrieve relevant knowledge in an end-to-end fashion without being dependent on intermediate modules such as object detectors or caption generators. We introduce a new pretraining task that is effective for learning knowledge retrieval with multimodal queries and also improves performance on downstream tasks. We demonstrate superior performance in retrieval on two datasets (ReMuQ and OK-VQA) under zero-shot settings as well as further improvements when finetuned on these datasets.

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keyluo2023end

Related papers

• REVEAL: Retrieval-augmented Visual-language Pre-training With Multi-source Multimodal Knowledge Memory (2022)13.65
• Recqr: Incorporating Conversational Query Rewriting To Improve Multimodal Image Retrieval (2026)0.00
• Cross-modal Retrieval For Knowledge-based Visual Question Answering (2024)7.81
• Cross-modal Retrieval Augmentation For Multi-modal Classification (2021)9.23
• Fine-grained Late-interaction Multi-modal Retrieval For Retrieval Augmented Visual Question Answering (2023)5.24
• Pixel-grounded Retrieval For Knowledgeable Large Multimodal Models (2026)0.00
• Mumur : Multilingual Multimodal Universal Retrieval (2022)2.26
• Pre-training Multi-modal Dense Retrievers For Outside-knowledge Visual Question Answering (2023)7.50