A DeiT transformer with multi-scale patch embedding, LoRA, knowledge distillation, and federated learning outperforms standard CNNs and transformers on OCTDL and Eye Disease Image Dataset benchmarks for ophthalmic diagnosis.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decentralized LoRA augmented transformer with multi-scale feature learning for secured eye diagnosis
A DeiT transformer with multi-scale patch embedding, LoRA, knowledge distillation, and federated learning outperforms standard CNNs and transformers on OCTDL and Eye Disease Image Dataset benchmarks for ophthalmic diagnosis.