Bayesian Volumetric Autoregressive Generative Models for Better Semisupervised Learning
Autor: | Guilherme Pombo, Robert Gray, John Ashburner, Parashkev Nachev, Thomas Varsavsky |
---|---|
Rok vydání: | 2019 |
Předmět: |
0303 health sciences
business.industry Computer science Bayesian probability Machine learning computer.software_genre 03 medical and health sciences Generative model 0302 clinical medicine Autoregressive model Probability distribution Artificial intelligence business computer 030217 neurology & neurosurgery Generative grammar 030304 developmental biology |
Zdroj: | Lecture Notes in Computer Science ISBN: 9783030322502 MICCAI (4) |
Popis: | Deep generative models are rapidly gaining traction in medical imaging. Nonetheless, most generative architectures struggle to capture the underlying probability distributions of volumetric data, exhibit convergence problems, and offer no robust indices of model uncertainty. By comparison, the autoregressive generative model PixelCNN can be extended to volumetric data with relative ease, it readily attempts to learn the true underlying probability distribution and it still admits a Bayesian reformulation that provides a principled framework for reasoning about model uncertainty. |
Databáze: | OpenAIRE |
Externí odkaz: |