EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Weighted Sampling with Frequency-Aware Spatial Attention for Imbalanced Image Classification

Shiqi Zhang, Peng Li iD

Journal of Imaging · 01.07.2026 · 12 (7) · 293

DOI: 10.3390/jimaging12070293 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 01.07.2026. Verfasst von Shiqi Zhang und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, China. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Class imbalance remains a critical challenge in image classification, where underrepresented classes often receive insufficient training attention and exhibit poor recognition performance. In this study, we propose a hybrid framework that combines weighted sampling with frequency-aware spatial attention (WSFSA) to address class imbalance at both the data and feature levels. The weighted sampler improves the training exposure of minority classes, while the frequency-aware spatial attention module incorporates class-frequency information into spatial attention to enhance discriminative feature responses for underrepresented classes. We evaluate the proposed method on four MedMNIST benchmarks, DermaMNIST, BloodMNIST, OrganCMNIST, and DermaMNIST-224, using a ResNet-18 backbone. Results show that WSFSA provides the clearest benefit on the severely imbalanced DermaMNIST and DermaMNIST-224 datasets, performing comparably to the strongest baseline methods while showing particular benefits under severe class imbalance. On OrganCMNIST, WSFSA provides moderate gains, while on BloodMNIST, where the imbalance effect is weaker, all methods perform similarly. Per-class analysis further shows that WSFSA improves sensitivity for several minority or difficult classes while maintaining high specificity across most classes. These findings suggest that combining sampling-level and feature-level rebalancing is a practical strategy for improving class-balanced recognition, particularly under severe class imbalance.

Schlagwörter

Stichwörter der Autor:innen

frequency attentionhybrid neural networkimbalanced classificationweighted sampler

Autor:innen und Institutionen

  • School of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, China.
  • Department of Earth and Planetary Sciences, Stanford University, Stanford, CA 94305, USA.

ORCID-Profile: Peng Li

Zitieren

APA

Zhang, S., & Li, P. (2026). Weighted Sampling with Frequency-Aware Spatial Attention for Imbalanced Image Classification. Journal of Imaging, 12(7), 293. https://doi.org/10.3390/jimaging12070293

Vancouver

Zhang S, Li P. Weighted Sampling with Frequency-Aware Spatial Attention for Imbalanced Image Classification. Journal of Imaging. 2026;12(7):293. doi:10.3390/jimaging12070293

BibTeX
@article{Zhang2026,
  author = {Zhang, Shiqi and Li, Peng},
  title = {Weighted Sampling with Frequency-Aware Spatial Attention for Imbalanced Image Classification},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {7},
  pages = {293},
  doi = {10.3390/jimaging12070293}
}
Kostenlos starten →