Search Results for author:
Found 4 papers, 3 papers with code
Content-Aware Differential Privacy with Conditional Invertible Neural Networks
Manipulation of the latent space leads to a modified image while preserving important details.
Posterior temperature optimized Bayesian models for inverse problems in medical imaging
In POTOBIM, we optimize both the parameters of the prior distribution and the posterior temperature with respect to reconstruction accuracy using Bayesian optimization with Gaussian process regression.
Posterior Temperature Optimization in Variational Inference for Inverse Problems
Bayesian methods feature useful properties for solving inverse problems, such as tomographic reconstruction.
Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Prior
We use a randomly initialized convolutional network as parameterization of the reconstructed image and perform gradient descent to match the observation, which is known as deep image prior.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
