Deep Learning on Small Datasets using Online Image Search

Deep Learning on Small Datasets using Online Image Search

Paper in proceedings (conference paper)

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.

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

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

KOLÁŘ, M.; HRADIŠ, M.; ZEMČÍK, P.

2017

04.04.2016

Comenius University in Bratislava

Bratislava

978-1-4503-3693-2

Proceedings of 32nd Spring Conference on Computer Graphics

1335-5694

Proceeding of Spring Conference on Computer Graphics

2016

32

Slovak Republic

87

93

7

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

SCCG_camera_ready_Kolar_ammended