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

Big neural networks trained on large datasets have advanced thestate-of-the-art for a large variety of challenging problems, improvingperformance by a large margin. However, under low memory and limitedcomputational power constraints, the accuracy on the same problems dropsconsiderable. In this paper, we propose a series of techniques thatsignificantly improve the accuracy of binarized neural networks (i.e networkswhere both the features and the weights are binary). We evaluate the proposedimprovements on two diverse tasks: fine-grained recognition (human poseestimation) and large-scale image recognition (ImageNet classification).Specifically, we introduce a series of novel methodological changes including:(a) more appropriate activation functions, (b) reverse-order initialization,(c) progressive quantization, and (d) network stacking and show that theseadditions improve existing state-of-the-art network binarization techniques,significantly. Additionally, for the first time, we also investigate the extentto which network binarization and knowledge distillation can be combined. Whentested on the challenging MPII dataset, our method shows a performanceimprovement of more than 4% in absolute terms. Finally, we further validate ourfindings by applying the proposed techniques for large-scale object recognitionon the Imagenet dataset, on which we report a reduction of error rate by 4%.

Improved training of binary networks for human pose estimation and image recognition