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

Group convolution works well with many deep convolutional neural networks(CNNs) that can effectively compress the model by reducing the number ofparameters and computational cost. Using this operation, feature maps ofdifferent group cannot communicate, which restricts their representationcapability. To address this issue, in this work, we propose a novel operationnamed Hierarchical Group Convolution (HGC) for creating computationallyefficient neural networks. Different from standard group convolution whichblocks the inter-group information exchange and induces the severe performancedegradation, HGC can hierarchically fuse the feature maps from each group andleverage the inter-group information effectively. Taking advantage of theproposed method, we introduce a family of compact networks called HGCNets.Compared to networks using standard group convolution, HGCNets have a hugeimprovement in accuracy at the same model size and complexity level. Extensiveexperimental results on the CIFAR dataset demonstrate that HGCNets obtainsignificant reduction of parameters and computational cost to achievecomparable performance over the prior CNN architectures designed for mobiledevices such as MobileNet and ShuffleNet.

HGC: Hierarchical Group Convolution for Highly Efficient Neural Network