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

Object detection is a major challenge in computer vision, involving bothobject classification and object localization within a scene. While deep neuralnetworks have been shown in recent years to yield very powerful techniques fortackling the challenge of object detection, one of the biggest challenges withenabling such object detection networks for widespread deployment on embeddeddevices is high computational and memory requirements. Recently, there has beenan increasing focus in exploring small deep neural network architectures forobject detection that are more suitable for embedded devices, such as Tiny YOLOand SqueezeDet. Inspired by the efficiency of the Fire microarchitectureintroduced in SqueezeNet and the object detection performance of thesingle-shot detection macroarchitecture introduced in SSD, this paperintroduces Tiny SSD, a single-shot detection deep convolutional neural networkfor real-time embedded object detection that is composed of a highly optimized,non-uniform Fire sub-network stack and a non-uniform sub-network stack ofhighly optimized SSD-based auxiliary convolutional feature layers designedspecifically to minimize model size while maintaining object detectionperformance. The resulting Tiny SSD possess a model size of 2.3MB (~26X smallerthan Tiny YOLO) while still achieving an mAP of 61.3% on VOC 2007 (~4.2% higherthan Tiny YOLO). These experimental results show that very small deep neuralnetwork architectures can be designed for real-time object detection that arewell-suited for embedded scenarios.

Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection