English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Channel pruning is one of the major compression approaches for deep neuralnetworks. While previous pruning methods have mostly focused on identifyingunimportant channels, channel pruning is considered as a special case of neuralarchitecture search in recent years. However, existing methods are eithercomplicated or prone to sub-optimal pruning. In this paper, we propose apruning framework that adaptively determines the number of each layer'schannels as well as the wights inheritance criteria for sub-network. Firstly,evaluate the importance of each block in the network based on the mean of thescaling parameters of the BN layers. Secondly, use the bisection method toquickly find the compact sub-network satisfying the budget. Finally, adaptivelyand efficiently choose the weight inheritance criterion that fits the currentarchitecture and fine-tune the pruned network to recover performance. AdaPrunerallows to obtain pruned network quickly, accurately and efficiently, takinginto account both the structure and initialization weights. We prune thecurrently popular CNN models (VGG, ResNet, MobileNetV2) on different imageclassification datasets, and the experimental results demonstrate theeffectiveness of our proposed method. On ImageNet, we reduce 32.8% FLOPs ofMobileNetV2 with only 0.62% decrease for top-1 accuracy, which exceeds allprevious state-of-the-art channel pruning methods. The code will be released.

AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance