Target-Oriented Deformation of Visual-Semantic Embedding Space

TL;DR

This paper introduces TOD-Net, a post-processing module that deforms the embedding space to improve cross-modal retrieval by emphasizing entity-specific concepts and handling diversity.

Contribution

The paper presents TOD-Net, a novel deformation network that enhances existing multimodal embeddings for better cross-modal retrieval performance.

Findings

Achieves state-of-the-art results on MSCOCO dataset.

Effectively emphasizes entity-specific concepts.

Handles higher diversity in retrieval tasks.

Abstract

Multimodal embedding is a crucial research topic for cross-modal understanding, data mining, and translation. Many studies have attempted to extract representations from given entities and align them in a shared embedding space. However, because entities in different modalities exhibit different abstraction levels and modality-specific information, it is insufficient to embed related entities close to each other. In this study, we propose the Target-Oriented Deformation Network (TOD-Net), a novel module that continuously deforms the embedding space into a new space under a given condition, thereby adjusting similarities between entities. Unlike methods based on cross-modal attention, TOD-Net is a post-process applied to the embedding space learned by existing embedding systems and improves their performances of retrieval. In particular, when combined with cutting-edge models, TOD-Net gains the state-of-the-art cross-modal retrieval model associated with the MSCOCO dataset. Qualitative analysis reveals that TOD-Net successfully emphasizes entity-specific concepts and retrieves diverse targets via handling higher levels of diversity than existing models.