EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Partitioned Memory Storage Inspired Few-Shot Class-Incremental Learning

Yimin Yin, Wanxia Deng, Jing Zhang, Xiayan Cheng, Jinghua Zhang iD

Entropy · 29.07.2026 · 28 (8) · 843

DOI: 10.3390/e28080843 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 29.07.2026. Verfasst von Yimin Yin und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Hunan First Normal University, Changsha 410205, China. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities, Outstanding Youth Project of the Hunan Provincial Department of Education, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current mainstream deep learning techniques exhibit an over-reliance on extensive training data and a lack of adaptability to the dynamic world, marking a considerable disparity from human intelligence. To bridge this gap, Few-Shot Class-Incremental Learning(FSCIL) has emerged, focusing on continuous learning of new categories with limited samples without forgetting old knowledge. Existing FSCIL studies typically use a single model to learn knowledge across all sessions, inevitably leading to the stability–plasticity dilemma. Unlike machines that usually consolidate all categories into a single parameter space, cortical memory organization suggests that different types of knowledge can be distributed and organized across specialized cortical regions. Inspired by this organization principle, our paper aims to develop a method that learns independent models for each session. It can inherently prevent catastrophic forgetting. During the testing stage, our method integrates Uncertainty Quantification (UQ) for model deployment. Our method provides a fresh viewpoint for FSCIL and demonstrates the state-of-the-art performance on CIFAR-100 and mini-ImageNet datasets.

Schlagwörter

Stichwörter der Autor:innen

deep learningfew-shot learningincremental learninginformation entropyuncertainty quantification

Autor:innen und Institutionen

  • School of Mathematics and Statistics, Hunan First Normal University, Changsha 410205, China.
  • Hunan Provincial University Key Laboratory for Big Data Analysis and Application, Hunan First Normal University, Changsha 410205, China.
  • College of Meteorology and Oceanography, National University of Defense Technology, Changsha 410073, China.
  • Key Laboratory of Computing and Stochastic Mathematics, Hunan Normal University, Changsha 410081, China.
  • College of Computer Science and Software Engineering, Hohai University, Nanjing 211100, China.

ORCID-Profile: Jinghua Zhang

Förderung

  • Fundamental Research Funds for the Central Universities
  • Outstanding Youth Project of the Hunan Provincial Department of Education
  • National Natural Science Foundation of China
  • Science and Technology Program of Hunan Province

Zitieren

APA

Yin, Y., Deng, W., Zhang, J., Cheng, X., & Zhang, J. (2026). Partitioned Memory Storage Inspired Few-Shot Class-Incremental Learning. Entropy, 28(8), 843. https://doi.org/10.3390/e28080843

Vancouver

Yin Y, Deng W, Zhang J, Cheng X, Zhang J. Partitioned Memory Storage Inspired Few-Shot Class-Incremental Learning. Entropy. 2026;28(8):843. doi:10.3390/e28080843

BibTeX
@article{Yin2026,
  author = {Yin, Yimin and Deng, Wanxia and Zhang, Jing and Cheng, Xiayan and Zhang, Jinghua},
  title = {Partitioned Memory Storage Inspired Few-Shot Class-Incremental Learning},
  journal = {Entropy},
  year = {2026},
  volume = {28},
  number = {8},
  pages = {843},
  doi = {10.3390/e28080843}
}
Kostenlos starten →