Detail výsledku
Deep Learning on Small Datasets using Online Image Search
Hradiš Michal, Ing., Ph.D., UPGM (FIT)
Zemčík Pavel, prof. Dr. Ing., dr. h. c., UAMT (FEKT), UPGM (FIT)
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.
convolutional neural network, deep learning, image classification, reinforcement learning
@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"
}Zpracování, rozpoznávání a zobrazování multimediálních a 3D dat, VUT, Vnitřní projekty VUT, FIT-S-14-2506, zahájení: 2014-01-01, ukončení: 2016-12-31, ukončen