A channel pruning algorithm that clusters CNN channels using a batch-normalization-derived distance metric and keeps one representative per cluster, achieving 45.9% FLOPs reduction on ResNet-50/ImageNet with 0.34% Top-5 accuracy drop.
Do deep nets really need to be deep?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks
A channel pruning algorithm that clusters CNN channels using a batch-normalization-derived distance metric and keeps one representative per cluster, achieving 45.9% FLOPs reduction on ResNet-50/ImageNet with 0.34% Top-5 accuracy drop.