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

Kalliatakis, Grigorios, Sticlaru, Anca, Stamatiadis, George, Ehsan, Shoaib, Leonardis, Ales, Gall, Juergen and McDonald-Maier, Klaus D. (2018) Material classification in the wild: 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. vol. 4, SciTePress. pp. 427-432 . (doi:10.5220/0006634804270432).

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.

This record has no associated files available for download.

Contributors

Author: Shoaib Ehsan

Download statistics