Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing

Cross-modal hashing(CMH) is a key technique in information retrieval, valued for its efficiency, low dimensionality, and minimal storage requirements. Despite notable progress in this field, challenges persist, particularly the reliance on large labeled datasets. This paper presents a novel domain a...

Full description

Bibliographic Details
Main Authors: Han, Zhichao, Azman, Azreen, Rina Mustaffa, Mas, Khalid, Fatimah
Format: Article
Language:English
Published: Springer 2025
Online Access:http://psasir.upm.edu.my/id/eprint/120694/
http://psasir.upm.edu.my/id/eprint/120694/1/120694.pdf
_version_ 1848868218957987840
author Han, Zhichao
Azman, Azreen
Rina Mustaffa, Mas
Khalid, Fatimah
author_facet Han, Zhichao
Azman, Azreen
Rina Mustaffa, Mas
Khalid, Fatimah
author_sort Han, Zhichao
building UPM Institutional Repository
collection Online Access
description Cross-modal hashing(CMH) is a key technique in information retrieval, valued for its efficiency, low dimensionality, and minimal storage requirements. Despite notable progress in this field, challenges persist, particularly the reliance on large labeled datasets. This paper presents a novel domain adaptation framework that leverages a limited set of labeled data from the source domain to guide the training of a large quantity of unlabeled data in the target domain. Our approach incorporates pseudo-label generation to iteratively refine semantic representations in the target domain, progressively narrowing the semantic gap between domains. Additionally, we propose a category-level contrastive learning(CLCL) method to address class conflict issues common in traditional instance-based contrastive learning. By generating category prototype representations, we enhance the model’s ability to discriminate between categories effectively. Moreover, our framework includes a comprehensive optimization objective that integrates pseudo-label generation loss, contrastive learning loss, and hash code learning loss, ensuring that the generated hash codes are both discrete and discriminative. Experimental results on benchmark datasets demonstrate the superiority of our approach over existing CMH methods.
first_indexed 2025-11-15T14:48:54Z
format Article
id upm-120694
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:48:54Z
publishDate 2025
publisher Springer
recordtype eprints
repository_type Digital Repository
spelling upm-1206942025-10-08T06:35:31Z http://psasir.upm.edu.my/id/eprint/120694/ Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing Han, Zhichao Azman, Azreen Rina Mustaffa, Mas Khalid, Fatimah Cross-modal hashing(CMH) is a key technique in information retrieval, valued for its efficiency, low dimensionality, and minimal storage requirements. Despite notable progress in this field, challenges persist, particularly the reliance on large labeled datasets. This paper presents a novel domain adaptation framework that leverages a limited set of labeled data from the source domain to guide the training of a large quantity of unlabeled data in the target domain. Our approach incorporates pseudo-label generation to iteratively refine semantic representations in the target domain, progressively narrowing the semantic gap between domains. Additionally, we propose a category-level contrastive learning(CLCL) method to address class conflict issues common in traditional instance-based contrastive learning. By generating category prototype representations, we enhance the model’s ability to discriminate between categories effectively. Moreover, our framework includes a comprehensive optimization objective that integrates pseudo-label generation loss, contrastive learning loss, and hash code learning loss, ensuring that the generated hash codes are both discrete and discriminative. Experimental results on benchmark datasets demonstrate the superiority of our approach over existing CMH methods. Springer 2025 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/120694/1/120694.pdf Han, Zhichao and Azman, Azreen and Rina Mustaffa, Mas and Khalid, Fatimah (2025) Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing. Applied Intelligence, 55 (11). art. no. 813. pp. 1-16. ISSN 0924-669X; eISSN: 1573-7497 https://link.springer.com/article/10.1007/s10489-025-06712-x?error=cookies_not_supported&code=de131270-5fa7-45c4-a827-9dede4ec6578 10.1007/s10489-025-06712-x
spellingShingle Han, Zhichao
Azman, Azreen
Rina Mustaffa, Mas
Khalid, Fatimah
Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing
title Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing
title_full Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing
title_fullStr Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing
title_full_unstemmed Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing
title_short Domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing
title_sort domain adaptation with category-level contrastive learning for semi-supervised cross-modal hashing
url http://psasir.upm.edu.my/id/eprint/120694/
http://psasir.upm.edu.my/id/eprint/120694/
http://psasir.upm.edu.my/id/eprint/120694/
http://psasir.upm.edu.my/id/eprint/120694/1/120694.pdf