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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Text-to-Chart Retrieval | CRBench Precise Query | R@19.74 | 12 | |
| Text-to-Chart Retrieval | VisText L1 Caption | R@588.1 | 12 | |
| Text-to-Chart Retrieval | VisText L2+L3 Caption | R@50.6474 | 12 | |
| Text-to-Chart Retrieval | CRBench Fuzzy Query | R@15.34 | 12 | |
| Text-to-Chart Retrieval | Chart-To-Text (test) | R@582.56 | 12 | |
| Retrieval | WebQA (test) | Recall@564.5 | 5 |