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 (DCNNs) have dominated the recentdevelopments in computer vision through making various record-breaking models.However, it is still a great challenge to achieve powerful DCNNs inresource-limited environments, such as on embedded devices and smart phones.Researchers have realized that 1-bit CNNs can be one feasible solution toresolve the issue; however, they are baffled by the inferior performancecompared to the full-precision DCNNs. In this paper, we propose a novelapproach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking theadvantage of Bayesian learning, a well-established strategy for hard problems,to significantly improve the performance of extreme 1-bit CNNs. We incorporatethe prior distributions of full-precision kernels and features into theBayesian framework to construct 1-bit CNNs in an end-to-end manner, which havenot been considered in any previous related methods. The Bayesian losses areachieved with a theoretical support to optimize the network simultaneously inboth continuous and discrete spaces, aggregating different losses jointly toimprove the model capacity. Extensive experiments on the ImageNet and CIFARdatasets show that BONNs achieve the best classification performance comparedto state-of-the-art 1-bit CNNs.

Bayesian Optimized 1-Bit CNNs