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

Recent improvements in object detection have shown potential to aid in taskswhere previous solutions were not able to achieve. A particular area isassistive devices for individuals with visual impairment. Whilestate-of-the-art deep neural networks have been shown to achieve superiorobject detection performance, their high computational and memory requirementsmake them cost prohibitive for on-device operation. Alternatively, cloud-basedoperation leads to privacy concerns, both not attractive to potential users. Toaddress these challenges, this study investigates creating an efficient objectdetection network specifically for OLIV, an AI-powered assistant for objectlocalization for the visually impaired, via micro-architecture designexploration. In particular, we formulate the problem of finding an optimalnetwork micro-architecture as an numerical optimization problem, where we findthe set of hyperparameters controlling the MobileNetV2-SSD networkmicro-architecture that maximizes a modified NetScore objective function forthe MSCOCO-OLIV dataset of indoor objects. Experimental results show that sucha micro-architecture design exploration strategy leads to a compact deep neuralnetwork with a balanced trade-off between accuracy, size, and speed, making itwell-suited for enabling on-device computer vision driven assistive devices forthe visually impaired.

Enabling Computer Vision Driven Assistive Devices for the Visually Impaired via Micro-architecture Design Exploration