Scipediacontent: Scipediacontent moved page Draft Content 430264625 to Kozlov Osokin 2019a

2021-01-21T14:36:45Z

Scipediacontent moved page Draft Content 430264625 to Kozlov Osokin 2019a

Scipediacontent: Created page with " == Abstract == In this work, we outline the set of problems, which any neural network for object detection faces when its development comes to the deployment stage and propo..."

2021-01-21T14:36:42Z

Created page with " == Abstract == In this work, we outline the set of problems, which any neural network for object detection faces when its development comes to the deployment stage and propo..."

New page

== Abstract ==

In this work, we outline the set of problems, which any neural network for object detection faces when its development comes to the deployment stage and propose methods to deal with such difficulties. We show that these practices allow one to get neural network for object detection, which can recognize two classes: vehicles and pedestrians and achieves more than 60 frames per second inference speed on Core\(^{\mathrm{TM}}\) i5-6500 CPU. The proposed model is built on top of the popular Single Shot MultiBox Object Detection framework but with substantial improvements, which were inspired by the discovered problems. The network has just 1.96 GMAC (GMAC â billions of multiply-accumulate operations) complexity and less than 7 MB model size. It is publicly available as a part of IntelÂ® OpenVINO\(^{\mathrm{TM}}\) Toolkit.

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1811.05894 http://arxiv.org/abs/1811.05894]

* [http://arxiv.org/pdf/1811.05894 http://arxiv.org/pdf/1811.05894]

* [http://link.springer.com/content/pdf/10.1007/978-3-030-29516-5_55 http://link.springer.com/content/pdf/10.1007/978-3-030-29516-5_55],
: [http://dx.doi.org/10.1007/978-3-030-29516-5_55 http://dx.doi.org/10.1007/978-3-030-29516-5_55] under the license http://www.springer.com/tdm

* [https://dblp.uni-trier.de/db/journals/corr/corr1811.html#abs-1811-05894 https://dblp.uni-trier.de/db/journals/corr/corr1811.html#abs-1811-05894],
: [https://arxiv.org/abs/1811.05894 https://arxiv.org/abs/1811.05894],
: [https://link.springer.com/chapter/10.1007%2F978-3-030-29516-5_55 https://link.springer.com/chapter/10.1007%2F978-3-030-29516-5_55],
: [http://arxiv.org/pdf/1811.05894.pdf http://arxiv.org/pdf/1811.05894.pdf],
: [https://academic.microsoft.com/#/detail/2969890494 https://academic.microsoft.com/#/detail/2969890494]

← Older revision	Revision as of 14:36, 21 January 2021
(No difference)

Kozlov Osokin 2019a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 430264625 to Kozlov Osokin 2019a

Scipediacontent: Created page with " == Abstract == In this work, we outline the set of problems, which any neural network for object detection faces when its development comes to the deployment stage and propo..."