EUVIMEDEUVIMED entdecken
Crossref

Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning

Shuo Li, Fang Liu, Licheng Jiao, Lingling Li, Puhua Chen, Xu Liu, Wenping Ma

IEEE Transactions on Circuits and Systems for Video Technology · 2025-05 · 35 (5) · 4991-5005

DOI: 10.1109/tcsvt.2025.3525545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-05. Verfasst von Shuo Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: Postdoctoral Fellowship Program of China Postdoctoral Science Foundation, China Postdoctoral Science Foundation, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-Shot Class-Incremental Learning (FSCIL) faces a huge stability-plasticity challenge due to continuously learning knowledge from new classes with a small number of training samples without forgetting the knowledge of previously seen old classes. To alleviate this challenge, we propose a novel method called Prompt-based Concept Learning (PCL) for FSCIL, which generalizes conceptual knowledge learned from old classes to new classes by simulating human learning capabilities. In our PCL, in the base session, we simultaneously learn common basic concepts from the training data and the class-concept weight of each class in a prompt learning manner, and in each incremental session, class-concept weights between new classes and previously learned basic concepts are learned to achieve incremental learning. Furthermore, in order to avoid catastrophic forgetting, we propose a distribution estimation module to retain feature distributions of previously seen classes and a data replay module to randomly sample features of previously seen classes in incremental sessions. We verify the effectiveness of our PCL on widely used benchmarks, such as miniImageNet, CIFAR-100, and CUB-200. Experimental results show that our PCL achieves competitive results compared with other state-of-the-art methods, especially we achieve an average accuracy of 94.02% across all sessions on the miniImageNet benchmark.

Förderung

  • Postdoctoral Fellowship Program of China Postdoctoral Science Foundation
  • China Postdoctoral Science Foundation
  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Joint Fund Project of National Natural Science Foundation of China
  • Program for Cheung Kong Scholars and Innovative Research Team in University
  • Fund for Foreign Scholars in University Research and Teaching Programs
  • Key Scientific Technological Innovation Research Project by Ministry of Education

Zitieren

APA

Li, S., Liu, F., Jiao, L., Li, L., Chen, P., Liu, X., & Ma, W. (2025). Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning. IEEE Transactions on Circuits and Systems for Video Technology, 35(5), 4991-5005. https://doi.org/10.1109/tcsvt.2025.3525545

Vancouver

Li S, Liu F, Jiao L, Li L, Chen P, Liu X, et al. Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(5):4991-5005. doi:10.1109/tcsvt.2025.3525545

BibTeX
@article{Li2025,
  author = {Li, Shuo and Liu, Fang and Jiao, Licheng and Li, Lingling and Chen, Puhua and Liu, Xu and Ma, Wenping},
  title = {Prompt-Based Concept Learning for Few-Shot Class-Incremental Learning},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {5},
  pages = {4991--5005},
  doi = {10.1109/tcsvt.2025.3525545}
}
Kostenlos starten →