In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
App. Res. of Comp. Accepted Paper
Vol. 41, 2024 No. 12

Semantics-based local attention visual transformer method on small datasets

Feng Xin1
Wang Junjie1
Zhong Sheng1
Fang Tingting2
1. School of Computer Science & Engineering, Chongqing University of Technology, Chongqing 400054, China
2. School of Artificial Intelligence, Southwest University, Chongqing 400715, China
DOI: 10.19734/j.issn.1001-3695.2023.11.0643

Abstract

Vision Transformer have achieved great success in various computer vision tasks. However, when training from scratch on a small data set, it cannot be compared with convolutional neural networks of the same scale. Image-based local attention methods can significantly improve the data efficiency of ViT, but will lose information between distant but related patches. To solve the above problems, this paper proposes a bidirectional parallel local attention visual Transformer method. The method first groups patches at the feature level and performs local attention within the groups to compensate for the information loss by exploiting the relationships between patches in the feature space. Secondly, in order to effectively fuse information between patches, semantic-based local attention and image-based local attention are combined in parallel to enhance the performance of the ViT model on small data through bidirectional adaptive learning. Experimental results show that this method achieves 97.93% and 85.80% accuracy on the CIFAR-10 and CIFAR-100 data sets respectively with a calculation amount of 15.2GFLOPs and a parameter amount of 57.2M. Compared with other methods, the bidirectional parallel local attention visual Transformer maintains the effectiveness of the attributes required for local attention while enhancing local guidance capabilities.

Foundation Support

重庆市自然科学基金面上项目(CSTB2022NSCQ-MSX0493)
重庆市技术创新与应用发展重点项目(cstc2021jscx-dxwtBX0018)
重庆理工大学研究生教育高质量发展项目(gzlcx20233200)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2023.11.0643
Publish at: Application Research of Computers Accepted Paper, Vol. 41, 2024 No. 12

Publish History

[2024-09-02] Accepted Paper

Cite This Article

冯欣, 王俊杰, 钟声, 等. 小数据集上基于语义的局部注意视觉Transformer方法 [J]. 计算机应用研究, 2024, 41 (12). (2024-09-11). https://doi.org/10.19734/j.issn.1001-3695.2023.11.0643. (Feng Xin, Wang Junjie, Zhong Sheng, et al. Semantics-based local attention visual transformer method on small datasets [J]. Application Research of Computers, 2024, 41 (12). (2024-09-11). https://doi.org/10.19734/j.issn.1001-3695.2023.11.0643. )

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)