App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 8

Multi-scale hybrid feature transform coding for image semantic communication

Wang Mingjun1,2,3
Yang Qinheng1
1. School of Automation and Information Engineering, Xi'an University of Technology, Xi'an Shaanxi 710048, China
2. Xi'an Key Laboratory of Wireless Optical Communication and Network Research, Xi'an Shaanxi 710048, China
3. School of Physics and Telecommunications Engineering, Shaanxi University of Technology, Hanzhong Shaanxi 723001, China
DOI: 10.19734/j.issn.1001-3695.2025.12.0521

Abstract

Image semantic communication relies on deep neural networks for end-to-end semantic representation and reconstruction. The network architecture largely determines system performance. However, existing architectures remain limited. CNN-based schemes struggle to model long-range pixel dependencies. Transformer-based schemes incur high computational cost and hinder efficient use. Hybrid architectures often adopt simple fusion criteria and may yield suboptimal decisions under channel noise. This paper proposed a Multi-Scale Hybrid Feature Transform (MHFT) for image semantic communication. MHFT constructed a dual-path architecture to balance global semantics and local details. The global path performs frequency-domain global modeling with low computational cost. The detail path enhances texture and edge representation in the spatial domain. This paper designed a Phased Multi-Evidence Fusion (PMEF) strategy. PMEF constructs fusion evidence in stages from feature intensity, discrepancy, and correlation. PMEF adaptively allocates path weights. It strengthens global–local collaborative modeling and improves robustness under noisy channels. Experimental results show consistent PSNR and MS-SSIM gains over representative methods across multiple channel conditions and bandwidth budgets. The proposed method achieves lower computational overhead and faster end-to-end encoding and decoding. These results demonstrate its effectiveness and application potential.

Foundation Support

国家自然科学基金重大研究计划培育项目(92052106)、国家自然科学基金(61771385)、陕西省重点产业链创新团队(2024RS-CXTD-12)、陕西省高等学校创新团队(24JP131)、西安市重点产业链关键核心技术攻关项目(103-433023062)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.12.0521
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 8

Publish History

[2026-04-22] Accepted Paper

Cite This Article

王明军, 杨沁衡. 面向图像语义通信的多尺度混合特征变换编码方法 [J]. 计算机应用研究, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0521. (Wang Mingjun, Yang Qinheng. Multi-scale hybrid feature transform coding for image semantic communication [J]. Application Research of Computers, 2026, 43 (8). (2026-04-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0521. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)