EUVIMEDEUVIMED entdecken
Crossref

Local Semantics Refinement of Adaptive Representations for Robust Noisy Label Learning

Yueer Lin, Yang Zhang, Jiao Hou, Zilu Wang, Zhigang Zeng

IEEE Transactions on Image Processing · 2026 · 35 · 5789-5803

DOI: 10.1109/tip.2026.3696107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Yueer Lin und 4 weiteren Autor:innen. Die Arbeit nennt 71 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Higher Education Stable Support Program General Project, Scientific Foundation for Youth Scholars of Shenzhen University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The success of deep learning models heavily depends on high-quality labeled data, yet noisy labels are inevitable in large-scale datasets. Existing methods often suffer from confirmation bias and overlook the informative value of hard but clean samples. To address these challenges, we propose Local Semantics Refinement of Adaptive Representations (LFDA), a novel framework that adaptively refines label quality by leveraging local feature consistency and representation alignment. LFDA introduces a Local Consistency Score module that evaluates the similarity among local samples in the latent space to distinguish clean from noisy labels. In addition, a confidence neighborhood is further constructed to provide local reference guidance, enabling more accurate identification and correction of noisy instances. To enhance semantic reliability, LFDA integrates a Reliability-Aware Representation Alignment (RRA) module that aligns high-confidence sample representations to implicitly refine low-confidence instances via soft supervision. Extensive experiments on both synthetic and real-world noisy datasets demonstrate that LFDA consistently outperforms state-of-the-art label noise learning methods. The results confirm its good robustness, generalization ability, and effectiveness in handling diverse and complex noise conditions.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Higher Education Stable Support Program General Project
  • Scientific Foundation for Youth Scholars of Shenzhen University

Zitieren

APA

Lin, Y., Zhang, Y., Hou, J., Wang, Z., & Zeng, Z. (2026). Local Semantics Refinement of Adaptive Representations for Robust Noisy Label Learning. IEEE Transactions on Image Processing, 35, 5789-5803. https://doi.org/10.1109/tip.2026.3696107

Vancouver

Lin Y, Zhang Y, Hou J, Wang Z, Zeng Z. Local Semantics Refinement of Adaptive Representations for Robust Noisy Label Learning. IEEE Transactions on Image Processing. 2026;35:5789-5803. doi:10.1109/tip.2026.3696107

BibTeX
@article{Lin2026,
  author = {Lin, Yueer and Zhang, Yang and Hou, Jiao and Wang, Zilu and Zeng, Zhigang},
  title = {Local Semantics Refinement of Adaptive Representations for Robust Noisy Label Learning},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {5789--5803},
  doi = {10.1109/tip.2026.3696107}
}
Kostenlos starten →