WCR is a new training regularizer that concentrates weight magnitudes onto few parameters to improve one-shot pruning robustness under aggressive sparsity.
U-net: Convolutional networks for biomedical image segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Weight Concentration Regularization for Improving Pruning Robustness Under High Sparsity
WCR is a new training regularizer that concentrates weight magnitudes onto few parameters to improve one-shot pruning robustness under aggressive sparsity.