Adaptive Centroid-Connected Structure Matching Network Based on Semi-Supervised Heterogeneous Domain

Zhoubao Sun (), Yanan Tang, Xin Zhang and Xiaodong Zhang
Additional contact information
Zhoubao Sun: School of Engineering Audit, Nanjing Audit University, Nanjing 211815, China
Yanan Tang: School of Engineering Audit, Nanjing Audit University, Nanjing 211815, China
Xin Zhang: School of Computer Science, Nanjing Audit University, Nanjing 211815, China
Xiaodong Zhang: School of Computer Science, Nanjing Audit University, Nanjing 211815, China

Mathematics, 2024, vol. 12, issue 24, 1-18

Abstract: Heterogeneous domain adaptation (HDA) utilizes the knowledge of the source domain to model the target domain. Although the two domains are semantically related, the problem of feature and distribution differences in heterogeneous data still needs to be solved. Most of the existing HDA methods only consider the feature or distribution problem but do not consider the geometric semantic information similarity between the domain structures, which leads to a weakened adaptive performance. In order to solve the problem, a centroid connected structure matching network (CCSMN) approach is proposed, which firstly maps the heterogeneous data into a shared public feature subspace to solve the problem of feature differences. Secondly, it promotes the overlap of domain centers and nodes of the same category between domains to reduce the positional distribution differences in the internal structure of data. Then, the supervised information is utilized to generate target domain nodes, and the geometric structural and semantic information are utilized to construct a centroid-connected structure with a reasonable inter-class distance. During the training process, a progressive and integrated pseudo-labeling is utilized to select samples with high-confidence labels and improve the classification accuracy for the target domain. Extensive experiments are conducted in text-to-image and image-to-image HDA tasks, and the results show that the CCSMN outperforms several state-of-the-art baseline methods. Compared with state-of-the-art HDA methods, in the text-to-image transfer task, the efficiency has increased by 8.05%; and in the image-to-image transfer task, the efficiency has increased by about 2%, which suggests that the CCSMN benefits more from domain geometric semantic information similarity.

Keywords: heterogeneous domain adaptation; semantically; heterogeneous; centroid-connected structure matching network; geometric semantic information (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/24/3986/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/24/3986/ (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:12:y:2024:i:24:p:3986-:d:1546940

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 ().