Publication detail

Deep Learning Concepts and Datasets for Image Recognition: Overview 2019

HORÁK, K.

Original Title

Deep Learning Concepts and Datasets for Image Recognition: Overview 2019

English Title

Deep Learning Concepts and Datasets for Image Recognition: Overview 2019

Type

conference paper

Language

en

Original Abstract

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.

English abstract

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.

Keywords

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

Released

14.08.2019

Publisher

SPIE

Location

Guangzhou, China

ISBN

9781510630758

Book

Proceedings of SPIE - The International Society for Optical Engineering

Edition

Volume 11179

Edition number

Article number 11179

Pages from

484

Pages to

491

Pages count

8

URL

Documents

BibTex


@inproceedings{BUT159588,
  author="Karel {Horák}",
  title="Deep Learning Concepts and Datasets for Image Recognition: Overview 2019",
  annote="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.",
  address="SPIE",
  booktitle="Proceedings of SPIE - The International Society for Optical Engineering",
  chapter="159588",
  doi="10.1117/12.2539806",
  edition="Volume 11179",
  howpublished="online",
  institution="SPIE",
  number="111791S",
  year="2019",
  month="august",
  pages="484--491",
  publisher="SPIE",
  type="conference paper"
}