App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 9

Open-vocabulary semantic segmentation method for perceptual domains based on regional consistency and fusion attention

Wang Lihui
Hao Daozhan
Key Laboratory of Micro-inertial Instrument and Advanced Navigation Technology, Ministry of Education, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
DOI: 10.19734/j.issn.1001-3695.2025.12.0527

Abstract

To address the limitations of CLIP's pre-trained features in insufficient localization capability and the difficulty in transferring image-level knowledge to pixel-level understanding for open-vocabulary semantic segmentation tasks, this paper proposes an open-vocabulary semantic segmentation method named ARC-CLIP. Firstly, a dynamic attention fusion mechanism based on regional consistency is constructed, which systematically introduces self-correlative attention into the fine-tuning paradigm. Dynamic weights are assigned to different image tokens according to regional semantic characteristics to achieve adaptive fusion of self-correlative and cross-correlative attention. Secondly, image and text features are fused to generate regional relation descriptors. Finally, a deep fine-tuning module for regional relation descriptors is designed to deeply integrate CLIP's image-text alignment prior into the deep layers of the decoder, balancing prior knowledge and task-specific knowledge to alleviate overfitting. Experimental results demonstrate that the proposed method achieves a harmonic Intersection over Union (hIoU) of 89.9% on the PASCAL VOC dataset and 42.7% on the COCO-Stuff dataset. This effectively improves the accuracy of open-vocabulary semantic segmentation and verifies the effectiveness of the proposed method.

Foundation Support

国家自然科学基金联合基金项目(U25A20375)
江苏省重点研发计划(BE2022389)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.12.0527
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 9

Publish History

[2026-05-29] Accepted Paper

Cite This Article

王立辉, 郝道展. 基于区域一致性与融合注意力的感知域开放词汇语义分割方法 [J]. 计算机应用研究, 2026, 43 (9). (2026-06-02). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0527. (Wang Lihui, Hao Daozhan. Open-vocabulary semantic segmentation method for perceptual domains based on regional consistency and fusion attention [J]. Application Research of Computers, 2026, 43 (9). (2026-06-02). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0527. )

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)