Cross-modal hashing with semantic deep embedding

View/ Open
File version
Accepted Manuscript (AM)
Author(s)
Yan, Cheng
Bai, Xiao
Wang, Shuai
Zhou, Jun
Hancock, Edwin R
Griffith University Author(s)
Year published
2019
Metadata
Show full item recordAbstract
Cross-modal hashing has demonstrated advantages on fast retrieval tasks. It improves the quality of hash coding by exploiting semantic correlation across different modalities. In supervised cross-modal hashing, the learning of hash function replies on the quality of extracted features, for which deep learning models have been adopted to replace the traditional models based on handcraft features. All deep methods, however, have not sufficiently explored semantic correlation of modalities for the hashing process. In this paper, we introduce a novel end-to-end deep cross-modal hashing framework which integrates feature and ...
View more >Cross-modal hashing has demonstrated advantages on fast retrieval tasks. It improves the quality of hash coding by exploiting semantic correlation across different modalities. In supervised cross-modal hashing, the learning of hash function replies on the quality of extracted features, for which deep learning models have been adopted to replace the traditional models based on handcraft features. All deep methods, however, have not sufficiently explored semantic correlation of modalities for the hashing process. In this paper, we introduce a novel end-to-end deep cross-modal hashing framework which integrates feature and hash-code learning into the same network. We take both between and within modalities data correlation into consideration, and propose a novel network structure and a loss function with dual semantic supervision for hash learning. This method ensures that the generated binary codes keep the semantic relationship of the original data points. Cross-modal retrieval experiments on commonly used benchmark datasets show that our method yields substantial performance improvement over several state-of-the-art hashing methods.
View less >
View more >Cross-modal hashing has demonstrated advantages on fast retrieval tasks. It improves the quality of hash coding by exploiting semantic correlation across different modalities. In supervised cross-modal hashing, the learning of hash function replies on the quality of extracted features, for which deep learning models have been adopted to replace the traditional models based on handcraft features. All deep methods, however, have not sufficiently explored semantic correlation of modalities for the hashing process. In this paper, we introduce a novel end-to-end deep cross-modal hashing framework which integrates feature and hash-code learning into the same network. We take both between and within modalities data correlation into consideration, and propose a novel network structure and a loss function with dual semantic supervision for hash learning. This method ensures that the generated binary codes keep the semantic relationship of the original data points. Cross-modal retrieval experiments on commonly used benchmark datasets show that our method yields substantial performance improvement over several state-of-the-art hashing methods.
View less >
Journal Title
NEUROCOMPUTING
Volume
337
Copyright Statement
© 2019 Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence which permits unrestricted, non-commercial use, distribution and reproduction in any medium, providing that the work is properly cited.
Subject
Engineering
Psychology