Detail publikace

Deep Learning Concepts and Datasets for Image Recognition: Overview 2019

HORÁK, K.

Originální název

Deep Learning Concepts and Datasets for Image Recognition: Overview 2019

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

We present basics of a deep learning concept and an overview of well-known deep learning concepts as general Convolutional Neural Networks, R-CNN family, Single Shot Multibox Detector, You Only Look Once architecture and the RetinaNet in the first part of this paper. The all mentioned architectures are described to quickly compare to each other regarding their suitability for given general task. Several selected datasets often used in deep learning competitions are listed in the subsequent chapters in more details. The most known of practically used and listed datasets are COCO, KITTI, PascalVOC and CityShapes. The overview serves as a comparison of the state-of-the-art deep learning methods.

Klíčová slova

Deep learning, dataset, image recognition, convolutional neural network, R-CNN, RetinaNet.

Autoři

HORÁK, K.

Vydáno

14. 8. 2019

Nakladatel

SPIE

Místo

Guangzhou, China

ISBN

9781510630758

Kniha

Proceedings of SPIE - The International Society for Optical Engineering

Edice

Volume 11179

Číslo edice

Article number 11179

ISSN

0277-786X

Periodikum

Proceedings of SPIE

Ročník

11179

Číslo

111791S

Stát

Spojené státy americké

Strany od

484

Strany do

491

Strany počet

8

URL

BibTex

@inproceedings{BUT159588,
  author="Karel {Horák}",
  title="Deep Learning Concepts and Datasets for Image Recognition: Overview 2019",
  booktitle="Proceedings of SPIE - The International Society for Optical Engineering",
  year="2019",
  series="Volume 11179",
  journal="Proceedings of SPIE",
  volume="11179",
  number="111791S",
  pages="484--491",
  publisher="SPIE",
  address="Guangzhou, China",
  doi="10.1117/12.2539806",
  isbn="9781510630758",
  issn="0277-786X",
  url="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85072601173&doi=10.1117%2f12.2539806&partnerID=40&md5=250c8c0254e4037ba7340dc71d2c6f09"
}

Dokumenty