Figure 3
From: Efficient few-shot machine learning for classification of EBSD patterns
Selected feature maps from the first convolution layer. Feature maps extracted from the grayscale model corresponding to the filters shown previously in Fig. 2. One input image per space group is shown. From top to bottom, the six space groups are \(Pm\overline{3}m\), \(Pm\overline{3}n\),\(Fm\overline{3}m\),\(Fd\overline{3}m\),\(Im\overline{3}m\), and \(Ia\overline{3}d\).
