MOON: Multi-Hash Codes Joint Learning for Cross-Media Retrieval

TL;DR

This paper introduces MOON, a novel method for cross-media retrieval that learns multiple hash codes of different lengths simultaneously, leveraging multimodal data, semantic labels, and learned hash codes to improve efficiency and performance.

Contribution

MOON is the first approach to learn multiple hash codes of varying lengths simultaneously without retraining, enhancing scalability and semantic discrimination in cross-media retrieval.

Findings

Outperforms recent shallow and deep methods on several databases.

Achieves high retrieval accuracy with multiple hash lengths in a unified framework.

Reduces computational cost by avoiding retraining for different hash lengths.

Abstract

In recent years, cross-media hashing technique has attracted increasing attention for its high computation efficiency and low storage cost. However, the existing approaches still have some limitations, which need to be explored. 1) A fixed hash length (e.g., 16bits or 32bits) is predefined before learning the binary codes. Therefore, these models need to be retrained when the hash length changes, that consumes additional computation power, reducing the scalability in practical applications. 2) Existing cross-modal approaches only explore the information in the original multimedia data to perform the hash learning, without exploiting the semantic information contained in the learned hash codes. To this end, we develop a novel Multiple hash cOdes jOint learNing method (MOON) for cross-media retrieval. Specifically, the developed MOON synchronously learns the hash codes with multiple lengths in a unified framework. Besides, to enhance the underlying discrimination, we combine the clues from the multimodal data, semantic labels and learned hash codes for hash learning. As far as we know, the proposed MOON is the first work to simultaneously learn different length hash codes without retraining in cross-media retrieval. Experiments on several databases show that our MOON can achieve promising performance, outperforming some recent competitive shallow and deep methods.