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

In this paper, we propose a novel Convolutional Neural Network (CNN)architecture for learning multi-scale feature representations with goodtradeoffs between speed and accuracy. This is achieved by using a multi-branchnetwork, which has different computational complexity at different branches.Through frequent merging of features from branches at distinct scales, ourmodel obtains multi-scale features while using less computation. The proposedapproach demonstrates improvement of model efficiency and performance on bothobject recognition and speech recognition tasks,using popular architecturesincluding ResNet and ResNeXt. For object recognition, our approach reducescomputation by 33% on object recognition while improving accuracy with 0.9%.Furthermore, our model surpasses state-of-the-art CNN acceleration approachesby a large margin in accuracy and FLOPs reduction. On the task of speechrecognition, our proposed multi-scale CNNs save 30% FLOPs with slightly betterword error rates, showing good generalization across domains. The codes areavailable at https://github.com/IBM/BigLittleNet

Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition