Retformer, a from-scratch transformer with CNN patch embedding, rotary position encoding, grouped query attention, and SwiGLU, reports 92% OCT and 94% fundus accuracy for Alzheimer's detection, surpassing several pretrained baselines on small datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
An Explainable Transformer Model for Alzheimer's Disease Detection Using Retinal Imaging
Retformer, a from-scratch transformer with CNN patch embedding, rotary position encoding, grouped query attention, and SwiGLU, reports 92% OCT and 94% fundus accuracy for Alzheimer's detection, surpassing several pretrained baselines on small datasets.