EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LEA: A Lightweight Local Enhanced Attention Module with Local-Competitive Spatial Recalibration for CNN-Based Agricultural Image Classification

Kepeng Luo, Zhanyi Lian, Xin Han, Yunfeng Wang

Applied Sciences · 09.11.2026 · 16 (21) · 11085

DOI: 10.3390/app162111085 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 09.11.2026. Verfasst von Kepeng Luo und 3 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Technologies R&D Program of Jiangsu.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Local Enhanced Attention (LEA) adds neighborhood aggregation to a learned spatial gate for CNN-based agricultural image classification. The module combines strip filtering, channel-wise normalization and sigmoid gating, followed by aggregation without additional learned parameters. In a seven-method PlantSeg comparison, LEA recorded the highest mean lesion CAM energy (41.612%) and tied with SE in mean pointing accuracy (52.054%). Its PlantVillage mean accuracy was 99.902%, compared with 99.883% for baseline. The measured ResNet-50 configuration added 0.946% parameters, with higher latency and memory use. Classification, binary CAM overlap and corruption results varied across settings. These results support the use of LEA in agricultural classification workflows that inspect disease-related spatial cues.

Förderung

  • Key Technologies R&D Program of Jiangsu

Zitieren

APA

Luo, K., Lian, Z., Han, X., & Wang, Y. (2026). LEA: A Lightweight Local Enhanced Attention Module with Local-Competitive Spatial Recalibration for CNN-Based Agricultural Image Classification. Applied Sciences, 16(21), 11085. https://doi.org/10.3390/app162111085

Vancouver

Luo K, Lian Z, Han X, Wang Y. LEA: A Lightweight Local Enhanced Attention Module with Local-Competitive Spatial Recalibration for CNN-Based Agricultural Image Classification. Applied Sciences. 2026;16(21):11085. doi:10.3390/app162111085

BibTeX
@article{Luo2026,
  author = {Luo, Kepeng and Lian, Zhanyi and Han, Xin and Wang, Yunfeng},
  title = {LEA: A Lightweight Local Enhanced Attention Module with Local-Competitive Spatial Recalibration for CNN-Based Agricultural Image Classification},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {21},
  pages = {11085},
  doi = {10.3390/app162111085}
}
Kostenlos starten →