Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment
This work addresses a specific bottleneck in multimodal retrieval for researchers and practitioners by focusing on complementary information, though it appears incremental as it builds on existing contrastive learning frameworks.
The paper tackles the problem of multimodal retrieval by addressing the neglect of complementary information in images compared to paired texts, proposing CIEA which extracts and aligns this information to achieve significant improvements over existing models.
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.