Attribute-Guided Network for Cross-Modal Zero-Shot Hashing

Ji, Zhong and Sun, Yuxin and Yu, Yunlong and Pang, Yanwei and Han, Jungong (2020) Attribute-Guided Network for Cross-Modal Zero-Shot Hashing. IEEE Transactions on Neural Networks and Learning Systems, 31 (1). pp. 321-330. ISSN 2162-237X

[img]
Preview
PDF (AgNet)
AgNet.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (4MB)

Abstract

Zero-shot hashing (ZSH) aims at learning a hashing model that is trained only by instances from seen categories but can generate well to those of unseen categories. Typically, it is achieved by utilizing a semantic embedding space to transfer knowledge from seen domain to unseen domain. Existing efforts mainly focus on single-modal retrieval task, especially image-based image retrieval (IBIR). However, as a highlighted research topic in the field of hashing, cross-modal retrieval is more common in real-world applications. To address the cross-modal ZSH (CMZSH) retrieval task, we propose a novel attribute-guided network (AgNet), which can perform not only IBIR but also text-based image retrieval (TBIR). In particular, AgNet aligns different modal data into a semantically rich attribute space, which bridges the gap caused by modality heterogeneity and zero-shot setting. We also design an effective strategy that exploits the attribute to guide the generation of hash codes for image and text within the same network. Extensive experimental results on three benchmark data sets (AwA, SUN, and ImageNet) demonstrate the superiority of AgNet on both cross-modal and single-modal zero-shot image retrieval tasks.

Item Type: Journal Article
Journal or Publication Title: IEEE Transactions on Neural Networks and Learning Systems
Additional Information: ©2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Uncontrolled Keywords: /dk/atira/pure/subjectarea/asjc/1700/1705
Subjects:
Departments: Faculty of Science and Technology > School of Computing & Communications
ID Code: 133785
Deposited By: ep_importer_pure
Deposited On: 22 Jun 2019 09:12
Refereed?: Yes
Published?: Published
Last Modified: 27 Feb 2020 04:53
URI: https://eprints.lancs.ac.uk/id/eprint/133785

Actions (login required)

View Item View Item