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

Dropout regularization has been widely used in deep learning but performsless effective for convolutional neural networks since the spatially correlatedfeatures allow dropped information to still flow through the networks. Somestructured forms of dropout have been proposed to address this but prone toresult in over or under regularization as features are dropped randomly. Inthis paper, we propose a targeted regularization method named TargetDrop whichincorporates the attention mechanism to drop the discriminative feature units.Specifically, it masks out the target regions of the feature maps correspondingto the target channels. Experimental results compared with the other methods orapplied for different networks demonstrate the regularization effect of ourmethod.

TargetDrop: A Targeted Regularization Method for Convolutional Neural Networks