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

Pruning has become a promising technique used to compress and accelerateneural networks. Existing methods are mainly evaluated on spare labelingapplications. However, dense labeling applications are those closer to realworld problems that require real-time processing on resource-constrained mobiledevices. Pruning for dense labeling applications is still a largely unexploredfield. The prevailing filter channel pruning method removes the entire filterchannel. Accordingly, the interaction between each kernel in one filter channelis ignored.  In this study, we proposed kernel cluster pruning (KCP) to prune denselabeling networks. We developed a clustering technique to identify the leastrepresentational kernels in each layer. By iteratively removing those kernels,the parameter that can better represent the entire network is preserved; thus,we achieve better accuracy with a decent model size and computation reduction.When evaluated on stereo matching and semantic segmentation neural networks,our method can reduce more than 70% of FLOPs with less than 1% of accuracydrop. Moreover, for ResNet-50 on ILSVRC-2012, our KCP can reduce more than 50%of FLOPs reduction with 0.13% Top-1 accuracy gain. Therefore, KCP achievesstate-of-the-art pruning results.

KCP: Kernel Cluster Pruning for Dense Labeling Neural Networks