A handcrafted contrast-normalization preprocessing layer, NeuRN, gives mixed and often large changes in cross-digit-domain classification accuracy, with no aggregate or statistical support for the claimed improvement.
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
REJECT 1representative citing papers
citing papers explorer
-
NeuRN: Neuro-inspired Domain Generalization for Image Classification
A handcrafted contrast-normalization preprocessing layer, NeuRN, gives mixed and often large changes in cross-digit-domain classification accuracy, with no aggregate or statistical support for the claimed improvement.