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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Mobile vision systems such as smartphones, drones, and augmented-realityheadsets are revolutionizing our lives. These systems usually run multipleapplications concurrently and their available resources at runtime are dynamicdue to events such as starting new applications, closing existing applications,and application priority changes. In this paper, we present NestDNN, aframework that takes the dynamics of runtime resources into account to enableresource-aware multi-tenant on-device deep learning for mobile vision systems.NestDNN enables each deep learning model to offer flexible resource-accuracytrade-offs. At runtime, it dynamically selects the optimal resource-accuracytrade-off for each deep learning model to fit the model's resource demand tothe system's available runtime resources. In doing so, NestDNN efficientlyutilizes the limited resources in mobile vision systems to jointly maximize theperformance of all the concurrently running applications. Our experiments showthat compared to the resource-agnostic status quo approach, NestDNN achieves asmuch as 4.2% increase in inference accuracy, 2.0x increase in video frameprocessing rate and 1.7x reduction on energy consumption.

NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision