loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Grigorios Kalliatakis 1 ; Anca Sticlaru 1 ; George Stamatiadis 1 ; Shoaib Ehsan 1 ; Ales Leonardis 2 ; Juergen Gall 3 and Klaus D. McDonald-Maier 1

Affiliations: 1 University of Essex, United Kingdom ; 2 University of Birmingham, United Kingdom ; 3 University of Bonn, Germany

Keyword(s): Material Classification, Synthesized Data, CNN.

Related Ontology Subjects/Areas/Topics: Color and Texture Analyses ; Computer Vision, Visualization and Computer Graphics ; Image and Video Analysis

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.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.214.184.69

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
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; ISSN 2184-4321, SciTePress, pages 427-432. DOI: 10.5220/0006634804270432

@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},
issn={2184-4321},
}

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
IS - 2184-4321
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