all AI news
A Proximal Algorithm for Network Slimming. (arXiv:2307.00684v2 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
As a popular channel pruning method for convolutional neural networks (CNNs),
network slimming (NS) has a three-stage process: (1) it trains a CNN with
$\ell_1$ regularization applied to the scaling factors of the batch
normalization layers; (2) it removes channels whose scaling factors are below a
chosen threshold; and (3) it retrains the pruned model to recover the original
accuracy. This time-consuming, three-step process is a result of using
subgradient descent to train CNNs. Because subgradient descent does not exactly …
algorithm arxiv cnn cnns convolutional neural networks cs.cv network networks neural networks normalization popular process pruning regularization scaling stage threshold trains