Stacking deep learning reaches 97.2% accuracy for olive disease images
A stacking ensemble combining EfficientNet, ResNet and MobileNet classified healthy and diseased olive leaf images with 97.21% accuracy on a ...
A stacking ensemble combining EfficientNet, ResNet and MobileNet classified healthy and diseased olive leaf images with 97.21% accuracy on a ...
A comparative study of sugar beet and maize seedling imagery found that a custom CNN outperformed classical classifiers, while U-Net ...
A knowledge-distilled pyramid transformer with reduced attention achieved F1-scores of 90.92%, 97.76% and 94.59% on three 32 × 32-pixel image-classification ...
A new method called Conflict-Aware Posterior Correction softens the hard masking used in partial-label learning, improving Top-1 accuracy by 1.01 ...
The StreetTree preprint provides more than 12 million street-tree images from 133 countries and tests show that pretrained vision models ...
EfficientNet-B0 classified six pavement-image categories with 89.8% accuracy on the study dataset, outperforming ResNet50 and supporting a derived road-condition index.
A hierarchical deep-learning framework classified five lung and colon tissue classes with 98.50% accuracy on LC25000 and 82.01% on the ...
A cross-validation study of 1,090 images from one public orange dataset found 99.12% ± 0.71% accuracy for ViT + PCA ...
An abstract reports that an uncertainty-aware proof-of-concept model classified 6,849 cervical-cell images with an AUC-ROC of 0.993, but synthetic auxiliary ...
A weighted training method that distinguishes likely shortcut examples improved AI robustness across four image and language benchmarks without adding ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine