Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?
share
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 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 widely used material databases of real-world images.
READ FULL TEXT