In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
Technology of Graphic & Image
|
App. Res. of Comp. Printed Article
Vol. 42, 2025 No. 5
1576-1582

Transfer-corrected and adaptive knowledge distillation for few-shot object detection

Zhang Yingjun
Xue Fan
Xie Binhong
Zhang Rui
College of Computer Science & Technology, Taiyuan University of Science & Technology, Taiyuan 030024, China
DOI: 10.19734/j.issn.1001-3695.2024.07.0275

Abstract

Few-shot object detection methods currently exist the model bias problem and the difficulty in distinguishing irrelevant knowledge in the transfer learning paradigm. To address these issues, this paper proposed a transfer-corrected and adaptive knowledge distillation for few-shot object detection(TCAD-FSOD). To tackle the bias issue, it designed object aware region proposal network(OA-RPN) and a distribution calibration module(DCM). OA-RPN used a background screening mechanism to correct biased results from the region proposal network(RPN). DCM used information from base class samples to assist in calibrating the biased distribution of novel classes. For the problem of detectors struggling to differentiate between class-irrelevant knowledge, it introduced an adaptive temperature knowledge distillation module(ATKD). ATKD employed an adaptive temperature generator for precise knowledge distillation, enabling the detector to progressively and explicitly learned the common knowledge related to recognition between base and novel classes. Experimental results show that TCAD-FSOD outperforms the latest known algorithms, achieving the highest improvement of up to 2.7% on the PASCAL VOC dataset and 0.7% on the COCO dataset. Additionally, it demonstrates the effectiveness of the TCAD-FSOD algorithm in alleviating model bias and enhancing the recognition capability for novel classes.

Foundation Support

山西省基础研究计划资助项目(面上)(20210302123216)
山西省产教融合研究生联合培养示范基地项目(2022JD11)
吕梁市引进高层次科技人才重点研发项目(2022RC08)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2024.07.0275
Publish at: Application Research of Computers Printed Article, Vol. 42, 2025 No. 5
Section: Technology of Graphic & Image
Pages: 1576-1582
Serial Number: 1001-3695(2025)05-039-1576-07

Publish History

[2025-05-05] Printed Article

Cite This Article

张英俊, 薛凡, 谢斌红, 等. 融合迁移校正与自适应知识蒸馏的小样本目标检测 [J]. 计算机应用研究, 2025, 42 (5): 1576-1582. (Zhang Yingjun, Xue Fan, Xie Binhong, et al. Transfer-corrected and adaptive knowledge distillation for few-shot object detection [J]. Application Research of Computers, 2025, 42 (5): 1576-1582. )

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)