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

Binarized convolutional neural networks (BCNNs) are widely used to improvememory and computation efficiency of deep convolutional neural networks (DCNNs)for mobile and AI chips based applications. However, current BCNNs are not ableto fully explore their corresponding full-precision models, causing asignificant performance gap between them. In this paper, we propose rectifiedbinary convolutional networks (RBCNs), towards optimized BCNNs, by combiningfull-precision kernels and feature maps to rectify the binarization process ina unified framework. In particular, we use a GAN to train the 1-bit binarynetwork with the guidance of its corresponding full-precision model, whichsignificantly improves the performance of BCNNs. The rectified convolutionallayers are generic and flexible, and can be easily incorporated into existingDCNNs such as WideResNets and ResNets. Extensive experiments demonstrate thesuperior performance of the proposed RBCNs over state-of-the-art BCNNs. Inparticular, our method shows strong generalization on the object tracking task.

RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs