EUVIMEDEUVIMED entdecken
Crossref

Enhancing Soil Classification With DropKey ‐Augmented Lightweight Transformers

Yan Zhang, Rui‐Feng Li, Lantao Huang, Feng‐Tao Liu

Concurrency and Computation: Practice and Experience · 2026-04 · 38 (7)

DOI: 10.1002/cpe.70662 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 23.03.2026. Verfasst von Yan Zhang und 3 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soil degradation significantly impacts global agricultural productivity, making accurate soil classification crucial for sustainable land management. To address limitations of traditional surveys and computationally intensive models, we propose a lightweight Vision Transformer integrating TinyViT's hierarchical compression with DropKey's dynamic sparse attention. This architecture enables high‐accuracy soil classification suitable for edge computing. A hybrid data augmentation strategy effectively mitigates class imbalance in soil datasets. Evaluation on 1915 soil images shows our model achieves 98.42% accuracy with only 5.40 M parameters and 1.19G FLOPs, outperforming mainstream counterparts. While limited by dataset scale and controlled lighting, DropKey proves particularly effective for soil texture analysis by filtering noise while preserving critical textural boundaries. This framework effectively balances accuracy and efficiency, thereby facilitating deployment on resource‐constrained devices.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, Y., Li, R., Huang, L., & Liu, F. (2026). Enhancing Soil Classification With DropKey ‐Augmented Lightweight Transformers. Concurrency and Computation: Practice and Experience, 38(7). https://doi.org/10.1002/cpe.70662

Vancouver

Zhang Y, Li R, Huang L, Liu F. Enhancing Soil Classification With DropKey ‐Augmented Lightweight Transformers. Concurrency and Computation: Practice and Experience. 2026;38(7). doi:10.1002/cpe.70662

BibTeX
@article{Zhang2026,
  author = {Zhang, Yan and Li, Rui‐Feng and Huang, Lantao and Liu, Feng‐Tao},
  title = {Enhancing Soil Classification With DropKey ‐Augmented Lightweight Transformers},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2026},
  volume = {38},
  number = {7},
  doi = {10.1002/cpe.70662}
}
Kostenlos starten →