Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Zhenghao Liu, Chenyan Xiong, Yuanhuiyi Lv, Zhiyuan Liu, Ge Yu• 2022

Related benchmarks

TaskDatasetResultRank
Text-to-Chart RetrievalCRBench Precise Query
R@19.74
12
Text-to-Chart RetrievalVisText L1 Caption
R@588.1
12
Text-to-Chart RetrievalVisText L2+L3 Caption
R@50.6474
12
Text-to-Chart RetrievalCRBench Fuzzy Query
R@15.34
12
Text-to-Chart RetrievalChart-To-Text (test)
R@582.56
12
RetrievalWebQA (test)
Recall@564.5
5
Showing 6 of 6 rows

Other info

Follow for update