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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Group Equivariant Convolutions (GConvs) enable convolutional neural networksto be equivariant to various transformation groups, but at an additionalparameter and compute cost. We investigate the filter parameters learned byGConvs and find certain conditions under which they become highly redundant. Weshow that GConvs can be efficiently decomposed into depthwise separableconvolutions while preserving equivariance properties and demonstrate improvedperformance and data efficiency on two datasets. All code is publicly availableat github.com/Attila94/SepGrouPy.

Exploiting Learned Symmetries in Group Equivariant Convolutions