Cross-Modality Hashing with Partial Correspondence

TL;DR

This paper proposes a cross-modality hashing method that effectively utilizes partially corresponding data to improve cross-media search performance, demonstrating superior results on benchmark datasets despite limited correspondence information.

Contribution

It introduces a novel approach for cross-modal hashing that leverages partial correspondence data, enhancing performance over existing methods.

Findings

Outperforms state-of-the-art hashing methods with less correspondence data

Effective on Wiki and NUS-WIDE datasets

Improves cross-media retrieval accuracy

Abstract

Learning a hashing function for cross-media search is very desirable due to its low storage cost and fast query speed. However, the data crawled from Internet cannot always guarantee good correspondence among different modalities which affects the learning for hashing function. In this paper, we focus on cross-modal hashing with partially corresponded data. The data without full correspondence are made in use to enhance the hashing performance. The experiments on Wiki and NUS-WIDE datasets demonstrates that the proposed method outperforms some state-of-the-art hashing approaches with fewer correspondence information.