EUVIMEDEUVIMED entdecken
Crossref

Leveraging Meta-Learning To Improve Unsupervised Domain Adaptation

Amirfarhad Farhadi, Arash Sharifi

The Computer Journal · 22.06.2024 · 67 (5) · 1838-1850

DOI: 10.1093/comjnl/bxad104 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Computer Journal, online erschienen am 01.11.2023. Verfasst von Amirfarhad Farhadi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 37 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised Domain Adaptation (UDA) techniques in real-world scenarios often encounter limitations due to their reliance on reducing distribution dissimilarity between source and target domains, assuming it leads to effective adaptation. However, they overlook the intricate factors causing domain shifts, including data distribution variations, domain-specific features and nonlinear relationships, thereby hindering robust performance in challenging UDA tasks. The Neuro-Fuzzy Meta-Learning (NF-ML) approach overcomes traditional UDA limitations with its flexible framework that adapts to intricate, nonlinear domain gaps without rigid assumptions. NF-ML enhances domain adaptation by selecting a UDA subset and optimizing their weights via a neuro-fuzzy system, utilizing meta-learning to efficiently adapt models to new domains using previously acquired knowledge. This approach mitigates domain adaptation challenges and bolsters traditional UDA methods’ performance by harnessing the strengths of multiple UDA methods to enhance overall model generalization. The proposed approach shows potential in advancing domain adaptation research by providing a robust and efficient solution for real-world domain shifts. Experiments on three standard image datasets confirm the proposed approach’s superiority over state-of-the-art UDA methods, validating the effectiveness of meta-learning. Remarkably, the Office+Caltech 10, ImageCLEF-DA and combined digit datasets exhibit substantial accuracy gains of 30.9%, 6.8% and 10.9%, respectively, compared with the best-second baseline UDA approach.

Zitieren

APA

Farhadi, A., & Sharifi, A. (2024). Leveraging Meta-Learning To Improve Unsupervised Domain Adaptation. The Computer Journal, 67(5), 1838-1850. https://doi.org/10.1093/comjnl/bxad104

Vancouver

Farhadi A, Sharifi A. Leveraging Meta-Learning To Improve Unsupervised Domain Adaptation. The Computer Journal. 2024;67(5):1838-1850. doi:10.1093/comjnl/bxad104

BibTeX
@article{Farhadi2024,
  author = {Farhadi, Amirfarhad and Sharifi, Arash},
  title = {Leveraging Meta-Learning To Improve Unsupervised Domain Adaptation},
  journal = {The Computer Journal},
  year = {2024},
  volume = {67},
  number = {5},
  pages = {1838--1850},
  doi = {10.1093/comjnl/bxad104}
}
Kostenlos starten →