Adding a frozen FMCE convergence-score head with a tuned weight can improve image-classification accuracy by up to about 1.16 percentage points, but the paper's own equations and tables conflict.
isec: An optimized deep learning model for image classification on edge computing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
FMCE-Net++: Feature Map Convergence Evaluation and Training
Adding a frozen FMCE convergence-score head with a tuned weight can improve image-classification accuracy by up to about 1.16 percentage points, but the paper's own equations and tables conflict.