CNN-transformer ensembles with weighted soft voting reach QWK 0.934 on APTOS 2019 while Grad-CAM++ and VLMs supply visual and textual explanations.
7514–7528
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models
CNN-transformer ensembles with weighted soft voting reach QWK 0.934 on APTOS 2019 while Grad-CAM++ and VLMs supply visual and textual explanations.