Research Repository

Material classification in the wild: Do synthesized training data generalise better than real-world training data?

Kalliatakis, Grigorios and Sticlaru, Anca and Stamatiadis, George and Ehsan, Shoaib and Leonardis, Ales and Gall, Juergen and McDonald-Maier, Klaus (2018) Material classification in the wild: Do synthesized training data generalise better than real-world training data? In: 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018), 2018-01-27 - 2018-01-29, Funchal, Madeira, Portugal.

[img]
Preview
Text
VISAPP_2018_158.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (334kB) | Preview

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.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 4: VISAPP
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Elements
Date Deposited: 30 Apr 2020 08:23
Last Modified: 30 Apr 2020 08:23
URI: http://repository.essex.ac.uk/id/eprint/27403

Actions (login required)

View Item View Item