Deep Cross-Modal Hashing

TL;DR

This paper introduces Deep Cross-Modal Hashing (DCMH), an end-to-end deep learning framework that jointly learns features and hash codes for improved multimedia retrieval performance.

Contribution

It presents a novel deep neural network-based approach that integrates feature learning and hash-code learning into a unified framework for cross-modal hashing.

Findings

DCMH outperforms existing methods on real datasets.

Achieves state-of-the-art accuracy in cross-modal retrieval.

End-to-end training improves feature and hash code quality.

Abstract

Due to its low storage cost and fast query speed, cross-modal hashing (CMH) has been widely used for similarity search in multimedia retrieval applications. However, almost all existing CMH methods are based on hand-crafted features which might not be optimally compatible with the hash-code learning procedure. As a result, existing CMH methods with handcrafted features may not achieve satisfactory performance. In this paper, we propose a novel cross-modal hashing method, called deep crossmodal hashing (DCMH), by integrating feature learning and hash-code learning into the same framework. DCMH is an end-to-end learning framework with deep neural networks, one for each modality, to perform feature learning from scratch. Experiments on two real datasets with text-image modalities show that DCMH can outperform other baselines to achieve the state-of-the-art performance in cross-modal retrieval applications.