GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
This work addresses multimodal search across text and images for AI applications, but it appears incremental as it builds on existing multimodal LLM approaches with improved training data.
The paper tackles the problem of Universal Multimodal Retrieval (UMR) by developing a multimodal LLM-based dense retriever called GME, which achieves state-of-the-art performance on a new benchmark, though no concrete numbers are provided in the abstract.
Universal Multimodal Retrieval (UMR) aims to enable search across various modalities using a unified model, where queries and candidates can consist of pure text, images, or a combination of both. Previous work has attempted to adopt multimodal large language models (MLLMs) to realize UMR using only text data. However, our preliminary experiments demonstrate that more diverse multimodal training data can further unlock the potential of MLLMs. Despite its effectiveness, the existing multimodal training data is highly imbalanced in terms of modality, which motivates us to develop a training data synthesis pipeline and construct a large-scale, high-quality fused-modal training dataset. Based on the synthetic training data, we develop the General Multimodal Embedder (GME), an MLLM-based dense retriever designed for UMR. Furthermore, we construct a comprehensive UMR Benchmark (UMRB) to evaluate the effectiveness of our approach. Experimental results show that our method achieves state-of-the-art performance among existing UMR methods. Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.