Rollable Latent Space for SAR Target Recognition of Un-seen Views.

This paper proposes rollable latent space (RLS) for synthetic aperture radar (SAR) target recognition of un-seen views. Scarce labeled data and limited viewing direction are critical issues in SAR target recognition.The RLS is a designed space in which rolling of latent features corresponds to 3D rotation of an object. Thus latent features of an arbitrary view can be inferred using those of different views. This characteristic further enables us to augment data from limited viewing in RLS. Experimental results in five vehicle classification of un-seen views show that an RLS-based classifier improves accuracies by 30% compared with a conventional network's one.