Collaborative Global-Local Structure Network With Knowledge Distillation for Imbalanced Data Classification
IEEE Transactions on Circuits and Systems for Video Technology · 2025-03 · 35 (3) · 2450-2460
DOI: 10.1109/tcsvt.2024.3487867 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-03. Verfasst von Feiyan Wu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Multi-expert networks have shown great superiority for imbalanced data classification tasks due to their complementary and diverse. We have summarized two aspects for further explorations: (1) uncontrollable results, arising from the performance differences of individual experts and variations in sample difficulty; (2) insufficient exploration of the internal data structure. These factors result in inconsistent model performance across different data distributions, thereby impact the model’s generalization ability. To address the above issues, we propose a Collaborative Global-Local Structure Network (CGL-Net) with knowledge distillation for imbalanced data classification. Firstly, CGL-Net, as a new framework, decouples the representation learning of imbalanced data into global and local structure, enhancing the controllability of integration model in a hierarchical manner. Secondly, CGL-Net innovatively combines knowledge distillation, data augmentation, and multiple expert networks, efficiently extracting the internal structure of the data and improving robust recognition on imbalanced data. In particular, the global structure learning introduces an independent student network that integrates knowledge from diverse experts, enabling the model to achieve comprehensive and balanced performance across categories in imbalanced data. The local structure learning incorporates augmented data, allowing the model to focus on discriminative regional learning of individual objects, thereby enhances the robust representation for imbalanced data. After completing these two sequential learning stages, the model hierarchically integrates knowledge to achieve robust recognition performance on imbalanced data. Extensive experiments on six benchmark datasets demonstrate that the proposed CGL-Net significantly outperforms recent state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wu, F., Liu, Z., Zhang, Z., Liu, J., & Wang, L. (2025). Collaborative Global-Local Structure Network With Knowledge Distillation for Imbalanced Data Classification. IEEE Transactions on Circuits and Systems for Video Technology, 35(3), 2450-2460. https://doi.org/10.1109/tcsvt.2024.3487867
Vancouver
Wu F, Liu Z, Zhang Z, Liu J, Wang L. Collaborative Global-Local Structure Network With Knowledge Distillation for Imbalanced Data Classification. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(3):2450-2460. doi:10.1109/tcsvt.2024.3487867
BibTeX
@article{Wu2025,
author = {Wu, Feiyan and Liu, Zhunga and Zhang, Zuowei and Liu, Jiaxiang and Wang, Longfei},
title = {Collaborative Global-Local Structure Network With Knowledge Distillation for Imbalanced Data Classification},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2025},
volume = {35},
number = {3},
pages = {2450--2460},
doi = {10.1109/tcsvt.2024.3487867}
}
EUVIMED