Saved in:
Bibliographic Details
Main Authors: Chen, Hao, Zhu, Lei, Zhu, Xinghui
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914981067358208
author Chen, Hao
Zhu, Lei
Zhu, Xinghui
author_facet Chen, Hao
Zhu, Lei
Zhu, Xinghui
contents Deep hashing, due to its low cost and efficient retrieval advantages, is widely valued in cross-modal retrieval. However, existing cross-modal hashing methods either explore the relationships between data points, which inevitably leads to intra-class dispersion, or explore the relationships between data points and categories while ignoring the preservation of inter-class structural relationships, resulting in the generation of suboptimal hash codes. How to maintain both intra-class aggregation and inter-class structural relationships, In response to this issue, this paper proposes a DCGH method. Specifically, we use proxy loss as the mainstay to maintain intra-class aggregation of data, combined with pairwise loss to maintain inter-class structural relationships, and on this basis, further propose a variance constraint to address the semantic bias issue caused by the combination. A large number of comparative experiments on three benchmark datasets show that the DCGH method has comparable or even better performance compared to existing cross-modal retrieval methods. The code for the implementation of our DCGH framework is available at https://github.com/donnotnormal/DCGH.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15387
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Class-guided Hashing for Multi-label Cross-modal Retrieval
Chen, Hao
Zhu, Lei
Zhu, Xinghui
Information Retrieval
Deep hashing, due to its low cost and efficient retrieval advantages, is widely valued in cross-modal retrieval. However, existing cross-modal hashing methods either explore the relationships between data points, which inevitably leads to intra-class dispersion, or explore the relationships between data points and categories while ignoring the preservation of inter-class structural relationships, resulting in the generation of suboptimal hash codes. How to maintain both intra-class aggregation and inter-class structural relationships, In response to this issue, this paper proposes a DCGH method. Specifically, we use proxy loss as the mainstay to maintain intra-class aggregation of data, combined with pairwise loss to maintain inter-class structural relationships, and on this basis, further propose a variance constraint to address the semantic bias issue caused by the combination. A large number of comparative experiments on three benchmark datasets show that the DCGH method has comparable or even better performance compared to existing cross-modal retrieval methods. The code for the implementation of our DCGH framework is available at https://github.com/donnotnormal/DCGH.
title Deep Class-guided Hashing for Multi-label Cross-modal Retrieval
topic Information Retrieval
url https://arxiv.org/abs/2410.15387