Cycle-consistent Deep Generative Hashing For Cross-modal Retrieval

Abstract

In this paper, we propose a novel deep generative approach to cross-modal retrieval to learn hash functions in the absence of paired training samples through the cycle consistency loss. Our proposed approach employs adversarial training scheme to lean a couple of hash functions enabling translation between modalities while assuming the underlying semantic relationship. To induce the hash codes with semantics to the input-output pair, cycle consistency loss is further proposed upon the adversarial training to strengthen the correlations between inputs and corresponding outputs. Our approach is generative to learn hash functions such that the learned hash codes can maximally correlate each input-output correspondence, meanwhile can also regenerate the inputs so as to minimize the information loss. The learning to hash embedding is thus performed to jointly optimize the parameters of the hash functions across modalities as well as the associated generative models. Extensive experiments on

Stats

• citations208
• S2 citations—
• github stars0
• HF likes0
• heat score17.40
• arxiv keywu2018cycle

Related papers

• Coupled Cyclegan: Unsupervised Hashing Network For Cross-modal Retrieval (2019)14.76
• Hashgan:attention-aware Deep Adversarial Hashing For Cross Modal Retrieval (2017)15.34
• Fusion-supervised Deep Cross-modal Hashing (2019)8.60
• Correlation Hashing Network For Efficient Cross-modal Retrieval (2016)11.67
• Deep Lifelong Cross-modal Hashing (2023)6.34
• Deep Class-guided Hashing For Multi-label Cross-modal Retrieval (2024)6.20
• Unsupervised Multi-modal Hashing For Cross-modal Retrieval (2019)8.35
• Unsupervised Generative Adversarial Cross-modal Hashing (2017)16.47