Applying a SparK-style masked autoencoder to a lightweight CNN improves retinal disease classification, but the AD/PD gains are weakened by participant overlap between pre-training and evaluation sets.
Cells10(11) (Oct 2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A BERT-Style Self-Supervised Learning CNN for Disease Identification from Retinal Images
Applying a SparK-style masked autoencoder to a lightweight CNN improves retinal disease classification, but the AD/PD gains are weakened by participant overlap between pre-training and evaluation sets.