# Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval

arXiv: https://arxiv.org/abs/1804.11013 · HTML: https://mlsanity.com/paper/1804.11013/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2018.

## Built on by (most cited first, 11 of 11)

- [Language-Driven Image Style Transfer](https://mlsanity.com/paper/2106.00178/) (2021)
- [LaT: Latent Translation with Cycle-Consistency for Video-Text Retrieval](https://mlsanity.com/paper/2207.04858/) (2022)
- [Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis](https://mlsanity.com/paper/2302.08706/) (2023)
- [Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing](https://mlsanity.com/paper/2112.06489/) (2021)
- [A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval](https://mlsanity.com/paper/2201.02772/) (2022)
- [Discriminative Semantic Transitive Consistency for Cross-Modal Learning](https://mlsanity.com/paper/2103.14103/) (2021)
- [Cross-modal Zero-shot Hashing by Label Attributes Embedding](https://mlsanity.com/paper/2111.04080/) (2021)
- [Deep Adversarial Inconsistent Cognitive Sampling for Multi-view Progressive Subspace Clustering](https://mlsanity.com/paper/2101.03783/) (2021)
- [Information-Theoretic Hashing for Zero-Shot Cross-Modal Retrieval](https://mlsanity.com/paper/2209.12491/) (2022)
- [Semantic-Cohesive Knowledge Distillation for Deep Cross-modal Hashing](https://mlsanity.com/paper/2510.09664/) (2025)
- [Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics](https://mlsanity.com/paper/2510.20068/) (2025)

## Abstract (arXiv)

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 a variety of large-scale cross-modal data sets demonstrate that our proposed method achieves better retrieval results than the state-of-the-arts.