Přístupnostní navigace
E-application
Search Search Close
Publication detail
KOLÁŘ, M. HRADIŠ, M. ZEMČÍK, P.
Original Title
Deep Learning on Small Datasets using Online Image Search
Type
conference paper
Language
English
Original Abstract
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.
Keywords
convolutional neural network, deep learning, image classification, reinforcement learning
Authors
KOLÁŘ, M.; HRADIŠ, M.; ZEMČÍK, P.
Released
4. 4. 2016
Publisher
Comenius University in Bratislava
Location
Bratislava
ISBN
978-1-4503-3693-2
Book
Proceedings of 32nd Spring Conference on Computer Graphics
1335-5694
Periodical
Proceeding of Spring Conference on Computer Graphics
Year of study
2016
Number
32
State
Slovak Republic
Pages from
87
Pages to
93
Pages count
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" }