EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative Learning from Semantically Confused Label Distribution via Auto-Encoding Variational Bayes

Xinhai Li, Chenxu Meng, Heng Zhou, Yi Guo, Bowen Xue, Tianzuo Yu, Yunan Lu

Electronics · 07.07.2025 · 14 (13) · 2736

DOI: 10.3390/electronics14132736 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 07.07.2025. Verfasst von Xinhai Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Project of China Southern Power Grid Company Limited.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Label Distribution Learning (LDL) has emerged as a powerful paradigm for addressing label ambiguity, offering a more nuanced quantification of the instance–label relationship compared to traditional single-label and multi-label learning approaches. This paper focuses on the challenge of noisy label distributions, which is ubiquitous in real-world applications due to the annotator subjectivity, algorithmic biases, and experimental errors. Existing related LDL algorithms often assume a linear combination of true and random label distributions when modeling the noisy label distributions, an oversimplification that fails to capture the practical generation processes of noisy label distributions. Therefore, this paper introduces an assumption that the noise in label distributions primarily arises from the semantic confusion between labels and proposes a novel generative label distribution learning algorithm to model the confusion-based generation process of both the feature data and the noisy label distribution data. The proposed model is inferred using variational methods and its effectiveness is demonstrated through extensive experiments across various real-world datasets, showcasing its superiority in handling noisy label distributions.

Förderung

  • Science and Technology Project of China Southern Power Grid Company Limited

Zitieren

APA

Li, X., Meng, C., Zhou, H., Guo, Y., Xue, B., Yu, T., & Lu, Y. (2025). Generative Learning from Semantically Confused Label Distribution via Auto-Encoding Variational Bayes. Electronics, 14(13), 2736. https://doi.org/10.3390/electronics14132736

Vancouver

Li X, Meng C, Zhou H, Guo Y, Xue B, Yu T, et al. Generative Learning from Semantically Confused Label Distribution via Auto-Encoding Variational Bayes. Electronics. 2025;14(13):2736. doi:10.3390/electronics14132736

BibTeX
@article{Li2025,
  author = {Li, Xinhai and Meng, Chenxu and Zhou, Heng and Guo, Yi and Xue, Bowen and Yu, Tianzuo and Lu, Yunan},
  title = {Generative Learning from Semantically Confused Label Distribution via Auto-Encoding Variational Bayes},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {13},
  pages = {2736},
  doi = {10.3390/electronics14132736}
}
Kostenlos starten →