App. Res. of Comp. Accepted Paper
Vol. 41, 2024 No. 6

Knowledge distillation algorithm based on spatial attention map

Wang Liyue1
Liu Yuan1,2
1. School of Artificial Intelligence & Computer Science, Jiangnan University, Wuxi Jiangsu 214122, China
2. Jiangsu Provincial Key Laboratory of Media Design & Software Technology, Wuxi Jiangsu 214122, China
DOI: 10.19734/j.issn.1001-3695.2023.10.0496

Abstract

The knowledge distillation algorithm has a great effect on the streamlining of deep neural networks. The current feature-based knowledge distillation algorithm either focuses on a single part for improvement and ignores other beneficial parts, or provides effective guidance for the part that a small model should focus on, which makes the distillation effect insufficient. In order to make full use of the beneficial information of the large model and process it to improve the knowledge conversion rate of the small model, we propose a new distillation algorithm. Firstly, using the conditional probability distribution to fit the feature spatial distribution of the large model’s middle layer, and then extract the spatial attention maps that tend to be similar after fitting together with other beneficial information. Finally, using the small convolutional layer, narrowing the gap between models, transmit the transformed information to the small model to achieve distillation. Experimental results show that the algorithm has the applicability of multiple teacher-student combinations and the generality of multiple data sets, and compared with the current more advanced distillation algorithms, the performance is improved by about 1.19% and the time is shortened by 0.16h. It has important engineering significance and wide application prospects for large networks’ optimization and the application of deep learning on low-resource devices.

Foundation Support

国家自然科学基金资助项目(61972182)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2023.10.0496
Publish at: Application Research of Computers Accepted Paper, Vol. 41, 2024 No. 6

Publish History

[2024-02-02] Accepted Paper

Cite This Article

王礼乐, 刘渊. 基于空间注意力图的知识蒸馏算法 [J]. 计算机应用研究, 2024, 41 (6). (2024-04-10). https://doi.org/10.19734/j.issn.1001-3695.2023.10.0496. (Wang Liyue, Liu Yuan. Knowledge distillation algorithm based on spatial attention map [J]. Application Research of Computers, 2024, 41 (6). (2024-04-10). https://doi.org/10.19734/j.issn.1001-3695.2023.10.0496. )

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)