A New Volumetric CNN for 3D Object Classification Based on Joint Multiscale Feature and Subvolume Supervised Learning Approaches

<div>Classification accuracy during the training on 12 views: (a) MS-VDCNN-I (D-4), (b) MS-VDCNN-II (D-5), (c) MS-VDCNN-III (D-6), and (d) MS-VDCNN-IV (D-7).</div>

Computational Intelligence and Neuroscience

fig8

Figure 8

Figure 8: A New Volumetric CNN for 3D Object Classification Based on Joint Multiscale Feature and Subvolume Supervised Learning Approaches 