Technology of Graphic & Image
|
1882-1887

PLSR:weakly supervised instance segmentation via pseudo-label self-refinement

Wu Shike
Liang Yuqi
School of Automation Science & Engineering, South China University of Technology, Guangzhou 510641, China

Abstract

Most weakly supervised instance segmentation(WSIS) methods have achieved decent performance in instance segmentation by leveraging the pseudo-labels generated from class activation maps and the multi-stage training strategies. However, these WSIS methods still face many challenges in detecting complete object. To solve the above problems, this paper proposed a WSIS method based on pseudo-label self-refinement(PLSR), which continuously refined the pseudo-labels of each branch by filtering and aggregating the proposals through its own results during the training process, ensuring and gradually improving the quality of pseudo-labels, and finally improving the performance of instance segmentation. The experiments were conducted on the Pascal VOC2012 and MS-COCO datasets, and comparing with existing WSIS methods on two datasets, the AP50 was improved by 1.6% and 1.9%, respectively. Experimental results show that the PLSR scheme can effectively utilize the shape information of the proposals and the semantic information of the network itself to improve the quality of pseudo-labels and achieve decent segmentation results, which finally improves the performance of WSIS.

Publish Information

DOI: 10.19734/j.issn.1001-3695.2022.10.0477
Publish at: Application Research of Computers Printed Article, Vol. 40, 2023 No. 6
Section: Technology of Graphic & Image
Pages: 1882-1887
Serial Number: 1001-3695(2023)06-045-1882-06

Publish History

[2023-01-02] Accepted Paper
[2023-06-05] Printed Article

Cite This Article

吴仕科, 梁宇琦. 基于伪标签自细化的弱监督实例分割 [J]. 计算机应用研究, 2023, 40 (6): 1882-1887. (Wu Shike, Liang Yuqi. PLSR:weakly supervised instance segmentation via pseudo-label self-refinement [J]. Application Research of Computers, 2023, 40 (6): 1882-1887. )

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)