CTNet reaches 99.97% accuracy on the RiceImage dataset.

Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Outcome: accuraciese0
Value: 99.97%e0
Setting: RiceImagee0

Not reportedTaxonMaterialGeneCompoundOrgan / stageInteractorInteractor roleSecond interactorSecond interactor roleTreatmentComparatorDirectionQualifier

Verbatim

e0
“On three controlled-collected datasets (PlantSeedling, RiceImage, and SoyBeanSeed) the corresponding accuracies are 97.45%, 99.97%, and 93.08%”
✓ located verbatim in the source · abstract, characters 1859–2001

Title

CTNet: A cognitive-inspired TriPercept CrossFusion self-distillation model for image classification in agricultural field

Bo Han; Heguang Sun; Wenqian Tang; et al. Artificial Intelligence in Agriculture 2026. doi:10.1016/j.aiia.2026.05.003

Other claims from this paper (7)

Method / resource CTNet achieves 99.03% accuracy on the augmented custom lychee disease dataset.
Method / resource CTNet attains 99.74% accuracy on the PlantVillage dataset.
Method / resource CTNet attains 91.81% accuracy on the CottonWeedID15 dataset.
Method / resource CTNet attains 99.52% accuracy on the PotatoLeafDisease dataset.
Method / resource CTNet reaches 97.45% accuracy on the PlantSeedling dataset.
Method / resource CTNet reaches 93.08% accuracy on the SoyBeanSeed dataset.
Method / resource CTNet consistently outperforms state-of-the-art classification methods across all benchmarks.

Record rev-5cd8eba4f425682bbd0649ea88a2f295934db0f2f8bb669e09c94c2226c3a74b · schema claims-v0.9 · position 6 in the model’s answer