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

We introduce an extremely computation-efficient CNN architecture namedShuffleNet, which is designed specially for mobile devices with very limitedcomputing power (e.g., 10-150 MFLOPs). The new architecture utilizes two newoperations, pointwise group convolution and channel shuffle, to greatly reducecomputation cost while maintaining accuracy. Experiments on ImageNetclassification and MS COCO object detection demonstrate the superiorperformance of ShuffleNet over other structures, e.g. lower top-1 error(absolute 7.8%) than recent MobileNet on ImageNet classification task, underthe computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNetachieves ~13x actual speedup over AlexNet while maintaining comparableaccuracy.

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices