EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimizing pre-training for multi-label classification via generalized target-aware source data selection

Kanyu Miyoshi, Ryotaro Shimizu, Linxin Song, Masayuki Goto

Neurocomputing · 2026-06 · 681 · 133405

DOI: 10.1016/j.neucom.2026.133405 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurocomputing, 2026-06. Verfasst von Kanyu Miyoshi und 3 weiteren Autor:innen. Die Arbeit nennt 107 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Japan Society for the Promotion of Science

Zitieren

APA

Miyoshi, K., Shimizu, R., Song, L., & Goto, M. (2026). Optimizing pre-training for multi-label classification via generalized target-aware source data selection. Neurocomputing, 681, 133405. https://doi.org/10.1016/j.neucom.2026.133405

Vancouver

Miyoshi K, Shimizu R, Song L, Goto M. Optimizing pre-training for multi-label classification via generalized target-aware source data selection. Neurocomputing. 2026;681:133405. doi:10.1016/j.neucom.2026.133405

BibTeX
@article{Miyoshi2026,
  author = {Miyoshi, Kanyu and Shimizu, Ryotaro and Song, Linxin and Goto, Masayuki},
  title = {Optimizing pre-training for multi-label classification via generalized target-aware source data selection},
  journal = {Neurocomputing},
  year = {2026},
  volume = {681},
  pages = {133405},
  doi = {10.1016/j.neucom.2026.133405}
}
Kostenlos starten →