App. Res. of Comp. Accepted Paper
Vol. 44, 2027 No. 1

Multi-prior-guided soft clustering for unsupervised semantic segmentation

Shi Ruihao
Wang Yixin
Qi Shuai
Ding Derui
School of Optical-Electrical & Computer Engineering, University of Shanghai for Science & Technology, Shanghai 200093, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0129

Abstract

Unsupervised semantic segmentation aims to achieve pixel-level semantic partitioning under completely label-free conditions. To address the difficulty of separating weak-boundary objects, semantic drift, and the lack of stable convergence constraints in clustering, this study proposes a multi-prior-guided soft-clustering segmentation method. The method designs a strong–weak coupled prior injection mechanism, incorporates depth, positional, and color priors into graph structure modeling and feature modulation, and performs spectral decomposition to obtain spectral embeddings with global structural consistency. On this basis, the method jointly optimizes soft clustering in the spectral space and cluster centers in the encoding space and introduces a local–global dual-view consistency constraint to improve intra-cluster compactness, inter-cluster separability, and clustering stability. Experimental results show that the proposed method achieves 57.1% Acc and 21.6% mIoU on the COCO-Stuff dataset, outperforming the baseline method by 5.2 and 2.2 percentage points, respectively. On the Cityscapes dataset, it achieves 68.6% Acc and 16.6% mIoU, outperforming the baseline by 5.6 and 0.7 percentage points, respectively. These results demonstrate the effectiveness of the proposed method for unsupervised semantic segmentation.

Foundation Support

国家自然科学基金资助项目(62373251)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0129
Publish at: Application Research of Computers Accepted Paper, Vol. 44, 2027 No. 1

Publish History

[2026-08-27] Accepted Paper

Cite This Article

石瑞浩, 王溢新, 祁帅, 等. 基于多先验知识的软聚类无监督语义分割 [J]. 计算机应用研究, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0129. (Shi Ruihao, Wang Yixin, Qi Shuai, et al. Multi-prior-guided soft clustering for unsupervised semantic segmentation [J]. Application Research of Computers, 2027, 44 (1). (2026-09-14). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0129. )

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)