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