EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prompt-based learning for few-shot class-incremental learning

Jicheng Yuan, Hang Chen, Songsong Tian, Wenfa Li, Lusi Li, Enhao Ning, Yugui Zhang

Alexandria Engineering Journal · 2025-05 · 120 · 287-295

DOI: 10.1016/j.aej.2025.02.008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Alexandria Engineering Journal, 2025-05. Verfasst von Jicheng Yuan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to incrementally learn new tasks from a limited number of labeled samples, while retaining knowledge of previously learned tasks, mimicking the way humans learn. In this paper

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yuan, J., Chen, H., Tian, S., Li, W., Li, L., Ning, E., & Zhang, Y. (2025). Prompt-based learning for few-shot class-incremental learning. Alexandria Engineering Journal, 120, 287-295. https://doi.org/10.1016/j.aej.2025.02.008

Vancouver

Yuan J, Chen H, Tian S, Li W, Li L, Ning E, et al. Prompt-based learning for few-shot class-incremental learning. Alexandria Engineering Journal. 2025;120:287-295. doi:10.1016/j.aej.2025.02.008

BibTeX
@article{Yuan2025,
  author = {Yuan, Jicheng and Chen, Hang and Tian, Songsong and Li, Wenfa and Li, Lusi and Ning, Enhao and Zhang, Yugui},
  title = {Prompt-based learning for few-shot class-incremental learning},
  journal = {Alexandria Engineering Journal},
  year = {2025},
  volume = {120},
  pages = {287--295},
  doi = {10.1016/j.aej.2025.02.008}
}
Kostenlos starten →