EUVIMEDEUVIMED entdecken
Crossref

Delving Into Generalizable Label Distribution Learning

Xingyu Zhao, Lei Qi, Yuexuan An, Xin Geng

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-10 · 47 (10) · 8708-8724

DOI: 10.1109/tpami.2025.3581552 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-10. Verfasst von Xingyu Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Jiangsu Science Foundation, National Natural Science Foundation of China, the Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Owing to the excellent capability in dealing with label ambiguity, Label Distribution Learning (LDL), as an emerging machine learning paradigm, has received extensive research in recent years. Though remarkable progress has been achieved in various tasks, one limitation with existing LDL methods is that they are all based on the i.i.d. assumption that training and test data are identically and independently distributed. As a result, they suffer obvious performance degradation and are no longer applicable when tested in out-of-distribution scenarios, which severely limits the application of LDL in many tasks. In this paper, we identify and investigate the Generalizable Label Distribution Learning (GLDL) problem. To handle such a challenging problem, we delve into the characteristics of GLDL and find that the label annotations changing with the variability of the domains is the underlying reason for the performance degradation of the existing methods. Inspired by this observation, we explore domain-invariant feature-label correlation information to reduce the impact of label annotations changing with domains and propose two practical methods. Extensive experiments verify the superior performance of the proposed methods. Our work fills the gap in benchmarks and techniques for practical GLDL problems.

Förderung

  • Jiangsu Science Foundation
  • National Natural Science Foundation of China
  • the Fundamental Research Funds for the Central Universities
  • High Performance Computing Platform of Nanjing University of Aeronautics and Astronautics
  • Big Data Computing Center of Southeast University

Zitieren

APA

Zhao, X., Qi, L., An, Y., & Geng, X. (2025). Delving Into Generalizable Label Distribution Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(10), 8708-8724. https://doi.org/10.1109/tpami.2025.3581552

Vancouver

Zhao X, Qi L, An Y, Geng X. Delving Into Generalizable Label Distribution Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(10):8708-8724. doi:10.1109/tpami.2025.3581552

BibTeX
@article{Zhao2025,
  author = {Zhao, Xingyu and Qi, Lei and An, Yuexuan and Geng, Xin},
  title = {Delving Into Generalizable Label Distribution Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {10},
  pages = {8708--8724},
  doi = {10.1109/tpami.2025.3581552}
}
Kostenlos starten →