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
Technology of Graphic & Image
|
App. Res. of Comp. Printed Article
Vol. 40, 2023 No. 5
1542-1547

Distilling object detectors via knowledge review and decouple

Zhang Yao
Pan Zhisong
School of Command & Control Engineering, Army Engineering University of PLA, Nanjing 210000, China
DOI: 10.19734/j.issn.1001-3695.2022.09.0430

Abstract

Current knowledge distillation algorithms only distill between the corresponding layers. In order to solve the problem and improve the performance of knowledge distillation, this paper first analyzed the inference of the low-level features of the teacher model on the high-level features of the student model. On this basis, this paper proposed a knowledge distillation method for object detectors, which is based on knowledge review and feature decouple. Firstly, it aligned and fused the high-level feature maps of the student model, then extracted attention maps on spatial and channel dimensions separately, so that the high-level features of students could learn the low-level and high-level knowledge of teachers progressively. Afterwards, it decoupled and distilled the foreground and background separately. Finally, it used a pyramid pooling to calculate the similarity between the features of the teacher model at different scales. This paper conducted experiments on different object detectors. Experiments show that the proposed method is simple but effective, and can be applied to a variety of different object detectors. RetinaNet and FCOS with backbone networks of ResNet-50 obtained 39.8% and 42.8% mAP on the COCO2017 dataset, respectively, which are 2.4% and 2.3% higher than the benchmark.

Foundation Support

国家自然科学基金资助项目(62076251)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2022.09.0430
Publish at: Application Research of Computers Printed Article, Vol. 40, 2023 No. 5
Section: Technology of Graphic & Image
Pages: 1542-1547
Serial Number: 1001-3695(2023)05-040-1542-06

Publish History

[2022-11-08] Accepted Paper
[2023-05-05] Printed Article

Cite This Article

张瑶, 潘志松. 基于知识回顾与特征解耦的目标检测蒸馏 [J]. 计算机应用研究, 2023, 40 (5): 1542-1547. (Zhang Yao, Pan Zhisong. Distilling object detectors via knowledge review and decouple [J]. Application Research of Computers, 2023, 40 (5): 1542-1547. )

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)