Material Classification in theWild: Do Synthesized Training Data Generalise Better than Real-world Training Data?

Grigorios Kalliatakis, Anca Sticlaru, George Stamatiadis, Shoaib Ehsan, Ales Leonardis, Juergen Gall, Klaus D. McDonald-Maier

2018

Abstract

We question the dominant role of real-world training images in the field of material classification by investigating whether synthesized data can generalise more effectively than real-world data. Experimental results on three challenging real-world material databases show that the best performing pre-trained convolutional neural network (CNN) architectures can achieve up to 91.03% mean average precision when classifying materials in cross-dataset scenarios. We demonstrate that synthesized data achieve an improvement on mean average precision when used as training data and in conjunction with pre-trained CNN architectures, which spans from  5% to  19% across three widely used material databases of real-world images.

Paper Citation

in Harvard Style

Kalliatakis G., Sticlaru A., Stamatiadis G., Ehsan S., Leonardis A., Gall J. and McDonald-Maier K. (2018). Material Classification in theWild: Do Synthesized Training Data Generalise Better than Real-world Training Data?. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 427-432. DOI: 10.5220/0006634804270432

in Bibtex Style

@conference{visapp18,
author={Grigorios Kalliatakis and Anca Sticlaru and George Stamatiadis and Shoaib Ehsan and Ales Leonardis and Juergen Gall and Klaus D. McDonald-Maier},
title={Material Classification in theWild: Do Synthesized Training Data Generalise Better than Real-world Training Data?},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP},
year={2018},
pages={427-432},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006634804270432},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP
TI - Material Classification in theWild: Do Synthesized Training Data Generalise Better than Real-world Training Data?
SN - 978-989-758-290-5
AU - Kalliatakis G.
AU - Sticlaru A.
AU - Stamatiadis G.
AU - Ehsan S.
AU - Leonardis A.
AU - Gall J.
AU - McDonald-Maier K.
PY - 2018
SP - 427
EP - 432
DO - 10.5220/0006634804270432
PB - SciTePress