Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval

TL;DR

This paper introduces SSAH, a self-supervised adversarial hashing method that improves cross-modal retrieval by aligning semantic representations across different data modalities using adversarial networks and semantic supervision.

Contribution

It is among the first to integrate adversarial learning into self-supervised cross-modal hashing, enhancing semantic correlation and retrieval accuracy.

Findings

Outperforms state-of-the-art methods on three benchmark datasets.

Effectively bridges the modality gap in cross-modal retrieval.

Preserves semantic relationships in both semantic and Hamming spaces.

Abstract

Thanks to the success of deep learning, cross-modal retrieval has made significant progress recently. However, there still remains a crucial bottleneck: how to bridge the modality gap to further enhance the retrieval accuracy. In this paper, we propose a self-supervised adversarial hashing (\textbf{SSAH}) approach, which lies among the early attempts to incorporate adversarial learning into cross-modal hashing in a self-supervised fashion. The primary contribution of this work is that two adversarial networks are leveraged to maximize the semantic correlation and consistency of the representations between different modalities. In addition, we harness a self-supervised semantic network to discover high-level semantic information in the form of multi-label annotations. Such information guides the feature learning process and preserves the modality relationships in both the common semantic space and the Hamming space. Extensive experiments carried out on three benchmark datasets validate that the proposed SSAH surpasses the state-of-the-art methods.