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

Deep convolutional neural networks have achieved remarkable success incomputer vision. However, deep neural networks require large computingresources to achieve high performance. Although depthwise separable convolutioncan be an efficient module to approximate a standard convolution, it oftenleads to reduced representational power of networks. In this paper, underbudget constraints such as computational cost (MAdds) and the parameter count,we propose a novel basic architectural block, ANTBlock. It boosts therepresentational power by modeling, in a high dimensional space,interdependency of channels between a depthwise convolution layer and aprojection layer in the ANTBlocks. Our experiments show that ANTNet built by asequence of ANTBlocks, consistently outperforms state-of-the-art low-costmobile convolutional neural networks across multiple datasets. On CIFAR100, ourmodel achieves 75.7% top-1 accuracy, which is 1.5% higher than MobileNetV2 with8.3% fewer parameters and 19.6% less computational cost. On ImageNet, our modelachieves 72.8% top-1 accuracy, which is 0.8% improvement, with 157.7ms (20%faster) on iPhone 5s over MobileNetV2.

ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification