In these frameworks, templates are constructed using an iterative process of template estimation and alignment, which is often computationally very expensive. Due in part to this shortcoming, most methods compute asingle template for the entire population of images, or a few templates for specific sub-groups of the data.

While optimization-based methods boast gen-eralizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature.

Neural Information Processing Systems http://nips.cc/

Recent methods introduce deep neural networks to predict the controlling parameters of hand-crafted geometric transformation models (e.g.

We demonstrate the effectiveness of our method on both simulated 2D images andreal3Dbrain magnetic resonance (MR) images.

We propose contrastive coding to learn shared, dense image representations, referredtoasCoMIRs (ContrastiveMultimodal ImageRepresentations).