EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

OpenPlant: A Large-Scale Benchmark Dataset for Agricultural Plant Classification Using CNNs, ViTs, and VLMs

Kaiqi Liu, Wei Sun iD, Guanping Wang iD, Quan Feng, Hui Li

Plants · 27.02.2026 · 15 (5) · 727

DOI: 10.3390/plants15050727 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plants, online erschienen am 27.02.2026. Verfasst von Kaiqi Liu und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou 730070, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Gansu Province Research-Industry Integration Science and Technology Innovation Empowerment Program, Central Government-Guided Local Science and Technology Development Funding Project, Gansu Province Modern Cold-Arid Characteristic Agriculture Medicinal Crop Industry Technology System.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate plant classification based on deep learning is important for precision agriculture, such as weed control, crop monitoring, and smart farming systems. The accuracies of deep learning models rely on datasets. Although many datasets have been proposed in recent decades, they have the common limitations in terms of scale, less environmental diversity, and challenges of data integration. To solve these problems, in this paper, we introduce a new dataset named OpenPlant, which is a large-scale and open dataset containing 635,176 RGB images across 1167 plant species. OpenPlant includes diverse growth stages of plants, plant structures, and environmental conditions, and its annotations were carefully verified to ensure quality. The proposed OpenPlant can be a benchmark for agricultural plant classification. In this paper, we benchmarked 10 widely used convolutional neural networks (CNNs), 6 vision transformers (ViTs), and 12 vision–language models (VLMs) to provide a comprehensive evaluation. The OpenPlant dataset offers a comprehensive benchmark for agricultural research using deep learning and the results provide insights into future directions.

Schlagwörter

Stichwörter der Autor:innen

agricultural datasetsdeep learningplant classificationprecision agriculturevision language models

Autor:innen und Institutionen

  • College of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou 730070, China.

ORCID-Profile: Wei Sun, Guanping Wang

Förderung

  • Gansu Province Research-Industry Integration Science and Technology Innovation Empowerment Program
  • Central Government-Guided Local Science and Technology Development Funding Project
  • Gansu Province Modern Cold-Arid Characteristic Agriculture Medicinal Crop Industry Technology System
  • Gansu Province Industrial Support Plan Projects of Department of Education
  • Gansu Science and Technology Plan

Zitieren

APA

Liu, K., Sun, W., Wang, G., Feng, Q., & Li, H. (2026). OpenPlant: A Large-Scale Benchmark Dataset for Agricultural Plant Classification Using CNNs, ViTs, and VLMs. Plants, 15(5), 727. https://doi.org/10.3390/plants15050727

Vancouver

Liu K, Sun W, Wang G, Feng Q, Li H. OpenPlant: A Large-Scale Benchmark Dataset for Agricultural Plant Classification Using CNNs, ViTs, and VLMs. Plants. 2026;15(5):727. doi:10.3390/plants15050727

BibTeX
@article{Liu2026,
  author = {Liu, Kaiqi and Sun, Wei and Wang, Guanping and Feng, Quan and Li, Hui},
  title = {OpenPlant: A Large-Scale Benchmark Dataset for Agricultural Plant Classification Using CNNs, ViTs, and VLMs},
  journal = {Plants},
  year = {2026},
  volume = {15},
  number = {5},
  pages = {727},
  doi = {10.3390/plants15050727}
}
Kostenlos starten →