EUVIMEDEUVIMED entdecken
Crossref

A Continual Self-Supervised Learning Framework Using a Decoder and a Clustering-Based Data Selection Method

Ryosuke Fujii, Naoki Masuyama, Yusuke Nojima, Chu Kiong Loo, Liew Wei Shiung

Journal of Advanced Computational Intelligence and Intelligent Informatics · 20.11.2026 · 30 (6) · 1846-1856

DOI: 10.20965/jaciii.2026.p1846 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Advanced Computational Intelligence and Intelligent Informatics, online erschienen am 20.11.2026. Verfasst von Ryosuke Fujii und 4 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Osaka Metropolitan University, Japan Society for the Promotion of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Continual learning aims to learn a sequence of tasks without forgetting the previously learned tasks. Promising methods for achieving continual learning include applying a replay buffer that stores previously learned samples in existing learning frameworks. Among these methods, lifelong unsupervised mixup (LUMP) interpolates the current task samples and samples from the replay buffer to prevent forgetting. LUMP randomly selects data for the replay buffer. This random selection is likely to have a negative effect on learning performance. In this study, we propose a clustering-based data selection method for the replay buffer. In addition, we introduce a denoising autoencoder to the self-supervised methods to improve the performance of the learning representations. We compare the clustering algorithms used in our framework and demonstrate the effectiveness of the proposed framework through computational experiments. Experimental results on CIFAR-100 and Tiny-ImageNet demonstrate that the proposed framework improves the average accuracy compared with LUMP while reducing forgetting. In particular, the CA+-based selection approach enhances the learning performance. The source code is available at https://github.com/Masuyama-lab/LUMP_SidAE_Clustering

Förderung

  • Osaka Metropolitan University
  • Japan Society for the Promotion of Science

Zitieren

APA

Fujii, R., Masuyama, N., Nojima, Y., Loo, C. K., & Shiung, L. W. (2026). A Continual Self-Supervised Learning Framework Using a Decoder and a Clustering-Based Data Selection Method. Journal of Advanced Computational Intelligence and Intelligent Informatics, 30(6), 1846-1856. https://doi.org/10.20965/jaciii.2026.p1846

Vancouver

Fujii R, Masuyama N, Nojima Y, Loo CK, Shiung LW. A Continual Self-Supervised Learning Framework Using a Decoder and a Clustering-Based Data Selection Method. Journal of Advanced Computational Intelligence and Intelligent Informatics. 2026;30(6):1846-1856. doi:10.20965/jaciii.2026.p1846

BibTeX
@article{Fujii2026,
  author = {Fujii, Ryosuke and Masuyama, Naoki and Nojima, Yusuke and Loo, Chu Kiong and Shiung, Liew Wei},
  title = {A Continual Self-Supervised Learning Framework Using a Decoder and a Clustering-Based Data Selection Method},
  journal = {Journal of Advanced Computational Intelligence and Intelligent Informatics},
  year = {2026},
  volume = {30},
  number = {6},
  pages = {1846--1856},
  doi = {10.20965/jaciii.2026.p1846}
}
Kostenlos starten →