Skip to yearly menu bar Skip to main content


Virtual presentation / poster accept

Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval

Zhenghao Liu · Chenyan Xiong · Yuanhuiyi Lv · Zhiyuan Liu · Ge Yu

Keywords: [ Universal Embedding Space ] [ Modality-Balanced Hard Negative Training ] [ Dense Retrieval ] [ Multi-Modal Retrieval ] [ Image Verbalization ] [ Applications ]


Abstract:

This paper presents Universal Vision-Language Dense Retrieval (UniVL-DR), which builds a unified model for multi-modal retrieval. UniVL-DR encodes queries and multi-modality resources in an embedding space for searching candidates from different modalities. To learn a unified embedding space for multi-modal retrieval, UniVL-DR proposes two techniques: 1) Universal embedding optimization strategy, which contrastively optimizes the embedding space using the modality-balanced hard negatives; 2) Image verbalization method, which bridges the modality gap between images and texts in the raw data space. UniVL-DR achieves the state-of-the-art on the multi-modal open-domain question answering benchmark, WebQA, and outperforms all retrieval models on the two subtasks, text-text retrieval and text-image retrieval. It demonstrates that universal multi-modal search is feasible to replace the divide-and-conquer pipeline with a united model and also benefits single/cross modality tasks. All source codes of this work are available at https://github.com/OpenMatch/UniVL-DR.

Chat is not available.