App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 6

Group-equivariant capsule network based on region-wise attention

Wang Chenyang
Song Yan
Zeng Ru
College of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
DOI: 10.19734/j.issn.1001-3695.2025.08.0406

Abstract

CapsNet offers advantages in modeling spatial hierarchical relationships, but it contains a large number of parameters and incurs high computational costs. Moreover, when forming primary capsules, the convolutional feature maps usually divide evenly by channels, which results in insufficient preservation of spatial information and inadequate modeling of regional feature correlations. To address these issues, this paper proposes a Group Equivariant CapsNet based on regional attention. This method introduces group convolution in the feature extraction stage, significantly reducing model parameters and improving the geometric consistency of feature expression by utilizing group symmetry. At the same time, it designs a region attention mechanism to optimize the composition process of primary capsules, adaptively enhancing the correlation between features within each region and thus more fully preserving spatial structural information. In addition, this paper rigorously proves the equivariance of the proposed model under spatial transformation theoretically, providing mathematical support for its robustness. The experimental results demonstrate that, compared with the standard CapsNet and its improved models, this method maintains stable or even higher classification accuracy in multi-class image classification tasks while reducing the average parameter count by about 7.2%, effectively improving the computational efficiency and generalization ability of the model. The research results verify the feasibility and superiority of combining regional attention with group equivariance in capsule network optimization.

Foundation Support

国家自然科学基金资助项目(62073223)
上海自然科学基金资助项目(22ZR1443400)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.08.0406
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 6

Publish History

[2026-02-05] Accepted Paper

Cite This Article

王晨阳, 宋燕, 曾入. 基于区域注意的群等变胶囊网络 [J]. 计算机应用研究, 2026, 43 (6). (2026-02-25). https://doi.org/10.19734/j.issn.1001-3695.2025.08.0406. (Wang Chenyang, Song Yan, Zeng Ru. Group-equivariant capsule network based on region-wise attention [J]. Application Research of Computers, 2026, 43 (6). (2026-02-25). https://doi.org/10.19734/j.issn.1001-3695.2025.08.0406. )

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)