Technology of Graphic & Image
|
App. Res. of Comp. Printed Article
Vol. 39, 2022 No. 10
3191-3195

MultiFormer: image classification network based on Transformer

Hu Jiea,b,c
Chang Minjiea,b,c
Xiong Zongquana,b,c
Xu Boyuana,b,c
Xie Lihaoa,b,c
Guo Dia,b,c
a. Hubei Key Laboratory of Advanced Technology for Automotive Components, b. Hubei Collaborative Innovation Center for Automotive Components Technology, c. Hubei Research Center for New Energy & Intelligent Connected Vehicle, Wuhan University of Technology, Wuhan 430070, China
DOI: 10.19734/j.issn.1001-3695.2022.03.0133

Abstract

In order to solve the disadvantage that the ViT cannot change the input patch size and the input patches are all single-scale information, this paper proposed an image classification network based on Transformer called MultiFormer. MultiFormer embedded small patches with different scales of inputting at each stage into large patches with rich semantic information through the AWS module. And it captured local and global attention alternately through the GLA-P module, preserving both fine-grained and coarse-grained features during embedding. This paper designed MultiFormer-tiny, -small and -base networks of three different sizes to achieve 81.1%, 82.2% and 83.2% top-1 accuracy respectively in ImageNet image classification experiments, the latter two models improve by 3.1% and 3.4% compared to the same volume of convolutional neural networks ResNet-50 and ResNet-101. MultiFormer-base offers 2.1% improvement with far fewer parameters and computational effort than the ViT-Base/16 model, and without the need for extensive data pre-training.

Foundation Support

湖北省技术创新专项(2019AEA169)
湖北省科技重大专项(2020AAA001)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2022.03.0133
Publish at: Application Research of Computers Printed Article, Vol. 39, 2022 No. 10
Section: Technology of Graphic & Image
Pages: 3191-3195
Serial Number: 1001-3695(2022)10-050-3191-05

Publish History

[2022-05-25] Accepted Paper
[2022-10-05] Printed Article

Cite This Article

胡杰, 昌敏杰, 熊宗权, 等. 基于Transformer的图像分类网络MultiFormer [J]. 计算机应用研究, 2022, 39 (10): 3191-3195. (Hu Jie, Chang Minjie, Xiong Zongquan, et al. MultiFormer: image classification network based on Transformer [J]. Application Research of Computers, 2022, 39 (10): 3191-3195. )

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)