A new metric combining NCA-based feature separability with a conv2/conv1 gradient ratio ranks medical image source models better than six existing metrics on most targets, though statistical significance is limited.
Cheplygina, Cats or cat scans: Transfer learning from natural or med- ical image source data sets?, Current Opinion in Biomedical Engineering 9 (2019) 21–27
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
On dataset transferability in medical image classification
A new metric combining NCA-based feature separability with a conv2/conv1 gradient ratio ranks medical image source models better than six existing metrics on most targets, though statistical significance is limited.