Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment

TL;DR

This paper introduces CIEA, a novel multimodal retrieval method that extracts and aligns complementary information from images and text, significantly improving retrieval performance by capturing differences often overlooked by existing models.

Contribution

CIEA is the first approach to explicitly extract and align complementary information in multimodal data, enhancing retrieval accuracy beyond existing models.

Findings

CIEA outperforms existing models in retrieval tasks.

The method effectively captures complementary information.

Ablation studies confirm the importance of each component.

Abstract

Multimodal retrieval has emerged as a promising yet challenging research direction in recent years. Most existing studies in multimodal retrieval focus on capturing information in multimodal data that is similar to their paired texts, but often ignores the complementary information contained in multimodal data. In this study, we propose CIEA, a novel multimodal retrieval approach that employs Complementary Information Extraction and Alignment, which transforms both text and images in documents into a unified latent space and features a complementary information extractor designed to identify and preserve differences in the image representations. We optimize CIEA using two complementary contrastive losses to ensure semantic integrity and effectively capture the complementary information contained in images. Extensive experiments demonstrate the effectiveness of CIEA, which achieves significant improvements over both divide-and-conquer models and universal dense retrieval models. We provide an ablation study, further discussions, and case studies to highlight the advancements achieved by CIEA. To promote further research in the community, we have released the source code at https://github.com/zengdlong/CIEA.