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

Depthwise convolution and grouped convolution has been successfully appliedto improve the efficiency of convolutional neural network (CNN). We suggestthat these models can be considered as special cases of a generalizedconvolution operation, named channel local convolution(CLC), where an outputchannel is computed using a subset of the input channels. This definitionentails computation dependency relations between input and output channels,which can be represented by a channel dependency graph(CDG). By modifying theCDG of grouped convolution, a new CLC kernel named interlaced groupedconvolution (IGC) is created. Stacking IGC and GC kernels results in aconvolution block (named CLC Block) for approximating regular convolution. Byresorting to the CDG as an analysis tool, we derive the rule for setting themeta-parameters of IGC and GC and the framework for minimizing thecomputational cost. A new CNN model named clcNet is then constructed using CLCblocks, which shows significantly higher computational efficiency and fewerparameters compared to state-of-the-art networks, when being tested using theImageNet-1K dataset. Source code is available athttps://github.com/dqzhang17/clcnet.torch .

clcNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions