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

The recent advances in Deep Neural Networks (DNNs) stem from theirexceptional performance across various domains. However, their inherent largesize hinders deploying these networks on resource-constrained devices likeedge, mobile, and IoT platforms. Strategies have emerged, from partial cloudcomputation offloading (split computing) to integrating early exits within DNNlayers. Our work presents an innovative unified approach merging early exitsand split computing. We determine the 'splitting layer', the optimal depth inthe DNN for edge device computations, and whether to infer on edge device or beoffloaded to the cloud for inference considering accuracy, computationalefficiency, and communication costs. Also, Image classification faces diverseenvironmental distortions, influenced by factors like time of day, lighting,and weather. To adapt to these distortions, we introduce I-SplitEE, an onlineunsupervised algorithm ideal for scenarios lacking ground truths and withsequential data. Experimental validation using Caltech-256 and Cifar-10datasets subjected to varied distortions showcases I-SplitEE's ability toreduce costs by a minimum of 55% with marginal performance degradation of atmost 5%.

I-SplitEE: Image classification in Split Computing DNNs with Early Exits