A pruning method that iteratively generates both layer-pruned and filter-pruned candidates, keeps the one with the highest CKA similarity to the parent, and achieves high FLOPs reduction on small ResNets.
Layermerge: Neural network depth compression through layer pruning and merging,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Pruning Everything, Everywhere, All at Once
A pruning method that iteratively generates both layer-pruned and filter-pruned candidates, keeps the one with the highest CKA similarity to the parent, and achieves high FLOPs reduction on small ResNets.