Detail publikace

Deep Learning on Small Datasets using Online Image Search

KOLÁŘ, M. HRADIŠ, M. ZEMČÍK, P.

Originální název

Deep Learning on Small Datasets using Online Image Search

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Our contribution has the ability to learn visual categories from fewer images than previous approaches. We do this by modifying the pseudolabel method which augments labelled training images with unlabelled images, to create a method capable of handling labelled training images as well as queried images, which are likely to belong to the desired class. This is achieved by modifying the weighting and selection processes. The presented method adapts the pseudolabel approach to allow the use of web-scale datasets of millions of images. The results are demonstrated on a toy problem&start=0&order=1 devised from the SUN 397 dataset, and on the full SUN 397 dataset expanded with images gathered from Google's image search without human intervention.

Klíčová slova

convolutional neural network, deep learning, image classification, reinforcement learning

Autoři

KOLÁŘ, M.; HRADIŠ, M.; ZEMČÍK, P.

Vydáno

4. 4. 2016

Nakladatel

Comenius University in Bratislava

Místo

Bratislava

ISBN

978-1-4503-3693-2

Kniha

Proceedings of 32nd Spring Conference on Computer Graphics

ISSN

1335-5694

Periodikum

Proceeding of Spring Conference on Computer Graphics

Ročník

2016

Číslo

32

Stát

Slovenská republika

Strany od

87

Strany do

93

Strany počet

7

URL

http://dl.acm.org/citation.cfm?id=2948633

BibTex

@inproceedings{BUT130963,
  author="Martin {Kolář} and Michal {Hradiš} and Pavel {Zemčík}",
  title="Deep Learning on Small Datasets using Online Image Search",
  booktitle="Proceedings of 32nd Spring Conference on Computer Graphics",
  year="2016",
  journal="Proceeding of Spring Conference on Computer Graphics",
  volume="2016",
  number="32",
  pages="87--93",
  publisher="Comenius University in Bratislava",
  address="Bratislava",
  doi="10.1145/2948628.2948633",
  isbn="978-1-4503-3693-2",
  issn="1335-5694",
  url="http://dl.acm.org/citation.cfm?id=2948633"
}