PLDH: Pseudo-Labels Based Deep Hashing

Huawen Liu (), Minhao Yin, Zongda Wu, Liping Zhao, Qi Li, Xinzhong Zhu and Zhonglong Zheng
Additional contact information
Huawen Liu: Department of Computer Science, Shaoxing University, Shaoxing 312000, China
Minhao Yin: School of Information Science and Technology, Northeast Normal University, Changchun 130024, China
Zongda Wu: Department of Computer Science, Shaoxing University, Shaoxing 312000, China
Liping Zhao: Department of Computer Science, Shaoxing University, Shaoxing 312000, China
Qi Li: Department of Computer Science, Shaoxing University, Shaoxing 312000, China
Xinzhong Zhu: School of Computer Science and Technology, Zhejiang Normal University, Jinhua 311231, China
Zhonglong Zheng: School of Computer Science and Technology, Zhejiang Normal University, Jinhua 311231, China

Mathematics, 2023, vol. 11, issue 9, 1-13

Abstract: Deep hashing has received a great deal of attraction in large-scale data analysis, due to its high efficiency and effectiveness. The performance of deep hashing models heavily relies on label information, which is very expensive to obtain. In this work, a novel end-to-end deep hashing model based on pseudo-labels for large-scale data without labels is proposed. The proposed hashing model consists of two major stages, where the first stage aims to obtain pseudo-labels based on deep features extracted by a pre-training deep convolution neural network. The second stage generates hash codes with high quality by the same neural network in the previous stage, coupled with an end-to-end hash layer, whose purpose is to encode data into a binary representation. Additionally, a quantization loss is introduced and interwound within these two stages. Evaluation experiments were conducted on two frequently-used image collections, CIFAR-10 and NUS-WIDE, with eight popular shallow and deep hashing models. The experimental results show the superiority of the proposed method in image retrieval.

Keywords: learning to hash; image retrieval; deep learning; nearest neighbor search; unsupervised learning; pseudo-label (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/9/2175/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/9/2175/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:9:p:2175-:d:1139874

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().