Deep Manifold Hashing: A Divide-and-Conquer Approach for Semi-Paired Unsupervised Cross-Modal Retrieval

TL;DR

This paper introduces Deep Manifold Hashing, a divide-and-conquer approach that effectively handles semi-paired unsupervised cross-modal retrieval by dividing the problem into three sub-tasks, improving over existing methods.

Contribution

The paper proposes a novel divide-and-conquer framework for semi-paired unsupervised cross-modal hashing, with specialized models for feature extraction, hash code learning, and hash function learning.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Effectively handles semi-paired data without full supervision.

Demonstrates robustness across different cross-modal retrieval scenarios.

Abstract

Hashing that projects data into binary codes has shown extraordinary talents in cross-modal retrieval due to its low storage usage and high query speed. Despite their empirical success on some scenarios, existing cross-modal hashing methods usually fail to cross modality gap when fully-paired data with plenty of labeled information is nonexistent. To circumvent this drawback, motivated by the Divide-and-Conquer strategy, we propose Deep Manifold Hashing (DMH), a novel method of dividing the problem of semi-paired unsupervised cross-modal retrieval into three sub-problems and building one simple yet efficiency model for each sub-problem. Specifically, the first model is constructed for obtaining modality-invariant features by complementing semi-paired data based on manifold learning, whereas the second model and the third model aim to learn hash codes and hash functions respectively. Extensive experiments on three benchmarks demonstrate the superiority of our DMH compared with the state-of-the-art fully-paired and semi-paired unsupervised cross-modal hashing methods.