Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval

TL;DR

This paper introduces an unsupervised deep learning framework called UCH that uses coupled CycleGANs to learn effective cross-modal hash codes for retrieval without labeled data, outperforming existing methods.

Contribution

The paper proposes a novel unsupervised coupled CycleGAN architecture for cross-modal hashing, integrating representation learning and hash code generation in a unified adversarial framework.

Findings

UCH outperforms state-of-the-art unsupervised methods on benchmark datasets.

The coupled CycleGAN architecture effectively learns cross-modal representations.

The method requires no labeled data for training.

Abstract

In recent years, hashing has attracted more and more attention owing to its superior capacity of low storage cost and high query efficiency in large-scale cross-modal retrieval. Benefiting from deep leaning, continuously compelling results in cross-modal retrieval community have been achieved. However, existing deep cross-modal hashing methods either rely on amounts of labeled information or have no ability to learn an accuracy correlation between different modalities. In this paper, we proposed Unsupervised coupled Cycle generative adversarial Hashing networks (UCH), for cross-modal retrieval, where outer-cycle network is used to learn powerful common representation, and inner-cycle network is explained to generate reliable hash codes. Specifically, our proposed UCH seamlessly couples these two networks with generative adversarial mechanism, which can be optimized simultaneously to learn representation and hash codes. Extensive experiments on three popular benchmark datasets show that the proposed UCH outperforms the state-of-the-art unsupervised cross-modal hashing methods.