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/

Zendy Plus

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

Zendy Tools

Zendy Open

Standard 3D convolution operations require much larger amounts of memory andcomputation cost than 2D convolution operations. The fact has hindered thedevelopment of deep neural nets in many 3D vision tasks. In this paper, weinvestigate the possibility of applying depthwise separable convolutions in 3Dscenario and introduce the use of 3D depthwise convolution. A 3D depthwiseconvolution splits a single standard 3D convolution into two separate steps,which would drastically reduce the number of parameters in 3D convolutions withmore than one order of magnitude. We experiment with 3D depthwise convolutionon popular CNN architectures and also compare it with a similar structurecalled pseudo-3D convolution. The results demonstrate that, with 3D depthwiseconvolutions, 3D vision tasks like classification and reconstruction can becarried out with more light-weighted neural networks while still deliveringcomparable performances.

3D Depthwise Convolution: Reducing Model Parameters in 3D Vision Tasks