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

Figure 11

Log-loss plots during the training on 12 views: (a) MS-VDCNN-I, (b) MS-VDCNN-II (c) MS-VDCNN-III, and (d) MS-VDCNN-IV.

(a)

(b)

(c)

(d)