Geodesy

Modal

Hamming code

Semantic feature

Semantic gap

Algorithm

Benchmark (surveying)

Polymer chemistry

Hash function

Embedded system

Computer security

Modality (human–computer interaction)

Computer science

Image retrieval

Semantics (computer science)

Hamming space

Decoding methods

Geography

Image (mathematics)

Bottleneck

Artificial intelligence

Block code

Information retrieval

Chemistry

Programming language

Deep learning

Consistency (knowledge bases)

Machine learning

Adversarial system

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.

Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval