Claim · model-written summary
The method attained 81.4% top-1 accuracy on the PlantCLEF 2015 dataset.
Not reportedTaxonMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorDirectionQualifier
Verbatim
e0“the method performed well on three popular FGVC datasets, namely, the Flavia , Oxford Flowers, and PlantCLEF 2015 datasets, with top-1 accuracies of 100 %, 99.2 %, and 81.4 %, respectively.”
Title
Yanqi Dong; Zhibin Ma; Jiali Zi; et al. Ecological Informatics 2025. doi:10.1016/j.ecoinf.2025.103029
Other claims from this paper (5)
- Method / resource The transformer attained 90.3% top-1 accuracy on a same-family tree species dataset.
- Method / resource The transformer attained 96.8% top-3 accuracy on a same-family tree species dataset.
- Method / resource The method attained 100% top-1 accuracy on the Flavia dataset.
- Method / resource The method attained 99.2% top-1 accuracy on the Oxford Flowers dataset.
- Method / resource Ablation experiments and module visualizations gave satisfactory results.