TLC collapses deep networks by linearizing neurons with positive batch normalization shifts and removing those with non-positive shifts, then retraining, achieving up to 70% layer removal on some models with small accuracy loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Till the Layers Collapse: Compressing a Deep Neural Network through the Lenses of Batch Normalization Layers
TLC collapses deep networks by linearizing neurons with positive batch normalization shifts and removing those with non-positive shifts, then retraining, achieving up to 70% layer removal on some models with small accuracy loss.