On the Adaptability of Unsupervised CNN-Based Deformable Image Registration to Unseen Image Domains

no code implementations • 不知道 2018 • Ferrante, E., Oktay, O., Glocker, B., and Milone, D. H.

Our experiments suggest that models learned in different domains can be transferred at the expense of a decrease in performance, and that oneshot learning in the context of unsupervised CNN-based registration is a valid alternative to achieve consistent registration performance when only a pair of images from the target domain is available.

Image Registration One-Shot Learning +2