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

Acceleration of convolutional neural network has received increasingattention during the past several years. Among various acceleration techniques,filter pruning has its inherent merit by effectively reducing the number ofconvolution filters. However, most filter pruning methods resort to tedious andtime-consuming layer-by-layer pruning-recovery strategy to avoid a significantdrop of accuracy. In this paper, we present an efficient filter pruningframework to solve this problem. Our method accelerates the network in one-steppruning-recovery manner with a novel optimization objective function, whichachieves higher accuracy with much less cost compared with existing pruningmethods. Furthermore, our method allows network compression with global filterpruning. Given a global pruning rate, it can adaptively determine the pruningrate for each single convolutional layer, while these rates are often set ashyper-parameters in previous approaches. Evaluated on VGG-16 and ResNet-50using ImageNet, our approach outperforms several state-of-the-art methods withless accuracy drop under the same and even much fewer floating-point operations(FLOPs).

A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks