EUVIMEDEUVIMED entdecken
Crossref

Tomato Leaf Disease Classification Using EfficientNet Enhanced with RefConv Structural Reparameterization, Efficient Channel Attention, and Lion Optimizer

Lijuan Shi, Haitang Li, Shiwen Zhang

Informatica · 06.08.2026 · 50 (14)

DOI: 10.31449/inf.v50i14.14124 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informatica, online erschienen am 06.08.2026. Verfasst von Lijuan Shi und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fine-grained classification of tomato leaf diseases faces challenges due to high inter-class similarity and insufficient model generalization ability. To address these issues, this paper proposes an improved EfficientNet architecture that fuses structural reparameterization, a lightweight channel attention mechanism, and an efficient optimization strategy. Specifically, the reparameterized refocus convolution (RefConv) module is introduced to enhance the extraction ability of subtle lesion textures. The original Squeeze-and-Excitation (SE) module is replaced with the efficient channel attention (ECA) mechanism to achieve lightweight channel feature recalibration. Meanwhile, the Lion optimizer is adopted to accelerate convergence and improve generalization performance on complex agricultural images. Experimental results show that the proposed method achieves 98.44% accuracy on the self-built tomato disease dataset, which is 4.22% higher than that of the baseline model EfficientNet-B0. Cross-species generalization tests further obtain 98.43% and 99.51% accuracy on apple and grape leaf disease datasets, respectively, verifying the robustness and transferability of the model.

Zitieren

APA

Shi, L., Li, H., & Zhang, S. (2026). Tomato Leaf Disease Classification Using EfficientNet Enhanced with RefConv Structural Reparameterization, Efficient Channel Attention, and Lion Optimizer. Informatica, 50(14). https://doi.org/10.31449/inf.v50i14.14124

Vancouver

Shi L, Li H, Zhang S. Tomato Leaf Disease Classification Using EfficientNet Enhanced with RefConv Structural Reparameterization, Efficient Channel Attention, and Lion Optimizer. Informatica. 2026;50(14). doi:10.31449/inf.v50i14.14124

BibTeX
@article{Shi2026,
  author = {Shi, Lijuan and Li, Haitang and Zhang, Shiwen},
  title = {Tomato Leaf Disease Classification Using EfficientNet Enhanced with RefConv Structural Reparameterization, Efficient Channel Attention, and Lion Optimizer},
  journal = {Informatica},
  year = {2026},
  volume = {50},
  number = {14},
  doi = {10.31449/inf.v50i14.14124}
}
Kostenlos starten →