In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.

Post-training quantization strategy for referring image segmentation

Yang Hang
Jiang Xiaoyan
Shanghai University of Engineering Science, School of Electronic & Electrical Engineering, Shanghai 201620, China

Abstract

Referencing Image Segmentation (RIS) aims to segment objects described by sentences in an image by integrating visual and linguistic information. This technique has strong application prospects in interactive image editing and language-guided human-machine interaction. However, existing solutions tend to explore high-performance models, neglecting practical applications on edge devices with limited resources. The design proposed an efficient post-training quantization (PTQ) framework to address this challenge. Specifically, the analysis identified the root cause of performance collapse caused by using the Round-To-Nearest (RTN) quantization method. Then the framework proposed a two-region balanced quantization strategy to solve the non-normal distribution of activation values after Softmax and GeLU operations in the visual encoder, and introduced a reordered grouping quantization strategy to tackle the quantization problems caused by outliers in the linear layers activation of the text encoder. Extensive experiments exploring different quantization bit widths on three benchmark datasets demonstrated the clear advantages of the proposed scheme over existing PTQ methods. As the first quantization scheme specifically for the RIS task, it confirmed the feasibility of efficiently deploying the RIS model to edge devices using the PTQ method.

Foundation Support

国家自然科学基金资助项目(U2033218)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.10.0437
Publish at: Application Research of Computers Accepted Paper, Vol. 42, 2025 No. 7

Publish History

[2025-03-11] Accepted Paper

Cite This Article

杨航, 姜晓燕. 针对图像指代分割的训练后量化策略 [J]. 计算机应用研究, 2025, 42 (7). (2025-03-14). https://doi.org/10.19734/j.issn.1001-3695.2024.10.0437. (Yang Hang, Jiang Xiaoyan. Post-training quantization strategy for referring image segmentation [J]. Application Research of Computers, 2025, 42 (7). (2025-03-14). https://doi.org/10.19734/j.issn.1001-3695.2024.10.0437. )

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)