Search Results for author:
Found 6 papers, 2 papers with code
HyperPredict: Estimating Hyperparameter Effects for Instance-Specific Regularization in Deformable Image Registration
Our approach which we call HyperPredict, implements a Multi-Layer Perceptron that learns the effect of selecting particular hyperparameters for registering an image pair by predicting the resulting segmentation overlap and measure of deformation smoothness.
Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance
The covariance can model changing uncertainty dependencies caused by structure in the image, such as edges or objects, and provides a new distance metric from the manifold of learned images.
Learning Structured Gaussians to Approximate Deep Ensembles
Similarly to distillation approaches, our single network is trained to maximise the probability of samples from pre-trained probabilistic models, in this work we use a fixed ensemble of networks.
Flexible Amortized Variational Inference in qBOLD MRI
We demonstrate that our approach enables the inference of smooth OEF and DBV maps, with a physiologically plausible distribution that can be adapted through specification of an informative prior distribution.
The GAN that Warped: Semantic Attribute Editing with Unpaired Data
Deep neural networks have recently been used to edit images with great success, in particular for faces.
Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration
Our method is designed for large respiratory motion by integrating sparse keypoint correspondences into a dense continuous optimization framework.
